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

    Neuronpedia

    INDEX
    Explanations

    neighbor and neighbors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ある
    0.57
    ：%
    0.54
    );
    0.53
    to
    0.52
    rained
    0.52
     INSEE
    0.51
    ;
    0.51
     identifica
    0.50
    0.50
     Tayyip
    0.49
    POSITIVE LOGITS
    AP
    0.59
    ре
    0.59
    I
    0.57
    उ
    0.56
    IC
    0.55
    Би
    0.55
    IM
    0.52
    אה
    0.52
    हे
    0.52
    جه
    0.50
    Act Density 0.001%

    No Known Activations