Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to self-awareness and self-consciousness in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows personal pronouns and "imperative"

    np_acts-logits-general · gemini-2.0-flash

    states of self and others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     auss
    -0.51
     bästa
    -0.50
    ManyToMany
    -0.49
    municipi
    -0.49
     vasto
    -0.48
    тивний
    -0.48
    ktory
    -0.47
    vable
    -0.47
    Ệ
    -0.47
    readline
    -0.46
    POSITIVE LOGITS
     cautious
    0.79
     subconsciously
    0.75
     unconsciously
    0.64
    contentLoaded
    0.64
     extra
    0.63
    rainian
    0.62
     scrutin
    0.62
     recher
    0.58
     wary
    0.58
    Rhestr
    0.57
    Act Density 0.314%

    No Known Activations