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

    Neuronpedia

    INDEX
    Explanations

    following specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addiction
    0.40
    ジア
    0.40
    JECT
    0.39
     analges
    0.39
     schizophrenia
    0.38
    Dieter
    0.38
    有机会
    0.38
     psychopath
    0.38
     ট্যাব
    0.38
     nen
    0.37
    POSITIVE LOGITS
     Drawn
    0.40
    ermo
    0.39
    itam
    0.38
    ’.
    0.37
     электрон
    0.37
    inta
    0.36
    柴
    0.36
     arba
    0.35
    ˊ
    0.34
    损失
    0.34
    Act Density 0.000%

    No Known Activations