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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     微
    -0.07
    sthrough
    -0.06
    _ACCESS
    -0.06
     ANAL
    -0.06
     Equity
    -0.06
    ّه
    -0.06
    提交
    -0.06
    том
    -0.06
     painter
    -0.06
     По
    -0.06
    POSITIVE LOGITS
    .series
    0.07
    }]
    0.06
    roc
    0.06
     علاق
    0.06
    Classification
    0.06
     FontStyle
    0.06
     FG
    0.06
    IELD
    0.06
    >Contact
    0.06
     Tucker
    0.06
    Act Density 0.000%

    No Known Activations