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

    Neuronpedia

    INDEX
    Explanations

    bindings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PASSWORD
    -0.08
    GW
    -0.07
    ��
    -0.07
    ipment
    -0.07
    verte
    -0.06
     Mater
    -0.06
    忍
    -0.06
    �
    -0.06
    &A
    -0.06
     clusters
    -0.06
    POSITIVE LOGITS
    .Many
    0.06
    NdEx
    0.06
     columnist
    0.06
     holster
    0.06
    comments
    0.06
    とい
    0.06
     Хар
    0.06
     Throw
    0.06
     IR
    0.06
    ........
    0.06
    Act Density 0.004%

    No Known Activations