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

    Neuronpedia

    INDEX
    Explanations

    exp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Action
    -0.07
     exit
    -0.07
    <?=
    -0.07
    (depth
    -0.07
    “If
    -0.07
    xfe
    -0.07
     ViewChild
    -0.07
     Pare
    -0.07
    立足
    -0.07
    iors
    -0.07
    POSITIVE LOGITS
     prompted
    0.07
    _some
    0.07
    _PARENT
    0.07
     kem
    0.07
    뿐만
    0.07
     travellers
    0.06
     Laurent
    0.06
    _neurons
    0.06
    �
    0.06
     OUTER
    0.06
    Act Density 0.002%

    No Known Activations