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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or annoyance

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

    pre-adolescent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.41
    KURZBESCHREIBUNG
    -0.36
    libft
    -0.34
    AutoScaleMode
    -0.34
    のですね
    -0.32
    DOCTYPE
    -0.32
    RegistryLite
    -0.32
    Hentet
    -0.32
    XmlRootElement
    -0.32
    RSpec
    -0.31
    POSITIVE LOGITS
    hilangan
    0.60
     ſon
    0.55
     CanadaChoose
    0.54
    новништво
    0.53
     ſei
    0.53
     ſol
    0.51
     myſelf
    0.49
    뀜
    0.49
     Monfieur
    0.49
    lijck
    0.49
    Act Density 0.055%

    No Known Activations