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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals or groups

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

    negation and biological terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.46
    vician
    -0.43
     lans
    -0.36
    centes
    -0.36
    fortunes
    -0.36
     CreateTagHelper
    -0.35
    liputi
    -0.33
    pherals
    -0.33
     patas
    -0.32
     schloss
    -0.32
    POSITIVE LOGITS
     Италијани
    0.55
    PreferredItem
    0.49
    #
    0.47
     Walkover
    0.47
    TagMode
    0.47
    Derbyniad
    0.46
    Personensuche
    0.46
    RTGC
    0.45
    cyklopedia
    0.45
    RTLU
    0.43
    Act Density 0.036%

    No Known Activations