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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal beliefs and self-reflection

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

    in addition, it is, this understanding, so why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    delwed
    -0.77
    Ӕ
    -0.76
     فريبيس
    -0.74
     TextAppearance
    -0.74
     ब्रेकडाउन
    -0.73
     queſta
    -0.71
     Administrativna
    -0.71
     autorytatywna
    -0.69
     BorderRadius
    -0.68
     Италијани
    -0.68
    POSITIVE LOGITS
     lisäksi
    0.40
    atorul
    0.37
     squad
    0.36
    handelt
    0.35
    hrer
    0.34
     刺繍
    0.33
     mierda
    0.32
    ándote
    0.31
    specifier
    0.31
     sungai
    0.31
    Act Density 0.086%

    No Known Activations