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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    626
    -0.06
    .DropTable
    -0.06
     жен
    -0.06
    *z
    -0.06
    ावन
    -0.06
    켓
    -0.06
    _separator
    -0.06
    Proceed
    -0.06
     blocker
    -0.05
    142
    -0.05
    POSITIVE LOGITS
    陈
    0.07
    0.07
    .Owner
    0.07
    _candidate
    0.07
     Attach
    0.07
    	transform
    0.06
    .tencent
    0.06
     Maison
    0.06
     supporting
    0.06
     атмос
    0.06
    Act Density 0.030%

    No Known Activations