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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rate
    -0.06
     overrun
    -0.06
    될
    -0.06
    .destroy
    -0.06
     متعدد
    -0.06
    Sometimes
    -0.06
    ニメ
    -0.06
     *
    -0.06
     heavier
    -0.06
    .turn
    -0.06
    POSITIVE LOGITS
    �
    0.06
     Phát
    0.06
    论坛
    0.06
     Traverse
    0.06
    irq
    0.06
     breaker
    0.06
    онів
    0.06
    独
    0.06
    pping
    0.06
    ога
    0.06
    Act Density 0.021%

    No Known Activations