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

    Neuronpedia

    INDEX
    Explanations

    First

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تج
    -0.08
    㥄
    -0.08
    ongoose
    -0.08
     photoshop
    -0.07
    توج
    -0.07
    짥
    -0.07
    _prepare
    -0.07
    дж
    -0.06
    essian
    -0.06
     Another
    -0.06
    POSITIVE LOGITS
     две
    0.08
    超出
    0.08
     javafx
    0.07
    第二
    0.07
    低い
    0.07
     failure
    0.07
    UFACT
    0.07
    /&
    0.07
    %A
    0.07
    Sat
    0.07
    Act Density 0.237%

    No Known Activations