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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ritel
    -0.06
    _to
    -0.06
    _customer
    -0.06
    .init
    -0.06
    	if
    -0.06
    .el
    -0.06
    monthly
    -0.06
    (IF
    -0.06
     molecular
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    毒
    0.07
    isseur
    0.06
    Samsung
    0.06
    GF
    0.06
    沒有
    0.06
    AuthToken
    0.06
     remain
    0.06
     Australians
    0.06
     yAxis
    0.06
     vivid
    0.06
    Act Density 0.087%

    No Known Activations