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

    Neuronpedia

    INDEX
    Explanations

    references to conspiracy theories involving political figures and groups

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

    start_of_turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.60
     MainAxisSize
    -0.59
     wireType
    -0.56
    MethodManager
    -0.55
    ReusableCell
    -0.54
     wcześ
    -0.53
    astéroïdes
    -0.53
     increí
    -0.53
     considérons
    -0.52
    UnknownFieldSet
    -0.52
    POSITIVE LOGITS
     Ganz
    0.37
    佐
    0.34
     dri
    0.34
     Ziel
    0.33
    allt
    0.33
     chal
    0.33
     tari
    0.33
     revolution
    0.33
    Wea
    0.33
    Xaml
    0.32
    Act Density 0.083%

    No Known Activations