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

    Neuronpedia

    INDEX
    Explanations

    Okay, followed by a response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ுகிறார்கள்
    0.74
    老的
    0.70
    品牌的
    0.68
    Caprio
    0.65
     ত্ব
    0.64
    ائرة
    0.62
     ওদের
    0.62
     inger
    0.62
    ጴ
    0.62
    ऊदी
    0.61
    POSITIVE LOGITS
    দম
    0.77
     −
    0.69
     ;$
    0.66
     /-
    0.65
    $-
    0.65
    $;
    0.64
    igold
    0.63
     failure
    0.63
    bail
    0.62
    locks
    0.62
    Act Density 0.068%

    No Known Activations