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

    Neuronpedia

    INDEX
    Explanations

    addr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الطفل
    -0.08
    溃
    -0.07
     disruptive
    -0.07
     narc
    -0.07
     nguyên
    -0.06
     الدكتور
    -0.06
    egrated
    -0.06
     ک
    -0.06
     charging
    -0.06
     isEqual
    -0.06
    POSITIVE LOGITS
     rack
    0.08
    _rotate
    0.07
    (body
    0.07
     ←
    0.07
    annotation
    0.07
    (alert
    0.07
    addons
    0.06
    yw
    0.06
    所有人
    0.06
    anzeigen
    0.06
    Act Density 0.000%

    No Known Activations