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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffc
    -0.07
    童
    -0.07
    CBD
    -0.07
    @g
    -0.06
    _keeper
    -0.06
     dying
    -0.06
     каз
    -0.06
     vod
    -0.06
    _operator
    -0.06
    axios
    -0.06
    POSITIVE LOGITS
    ء
    0.06
    /mail
    0.06
    _hosts
    0.06
    .subscriptions
    0.06
     nhằm
    0.06
    安全
    0.06
     sponsor
    0.06
     estar
    0.06
     ':'
    0.06
     �
    0.06
    Act Density 0.038%

    No Known Activations