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

    Neuronpedia

    INDEX
    Explanations

    SE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alone
    -0.07
     mein
    -0.07
    rename
    -0.06
    (Sub
    -0.06
     논
    -0.06
    atitis
    -0.06
     Lutheran
    -0.06
    /Peak
    -0.06
    ModelState
    -0.06
    Notify
    -0.06
    POSITIVE LOGITS
    .asset
    0.06
    (#
    0.06
    	tag
    0.06
    >Email
    0.06
    образ
    0.06
     �
    0.06
     Defender
    0.06
    _PRICE
    0.06
    ：<
    0.05
    .gstatic
    0.05
    Act Density 0.051%

    No Known Activations