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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     head
    -0.06
    /perl
    -0.06
    "errors
    -0.06
    کی
    -0.06
     时间
    -0.06
    swick
    -0.06
    oneksi
    -0.06
    _pl
    -0.06
     drove
    -0.06
    estic
    -0.06
    POSITIVE LOGITS
    @param
    0.08
    Secret
    0.07
     nab
    0.07
    Catalog
    0.07
    Instant
    0.07
     ambiente
    0.06
    Fact
    0.06
    Low
    0.06
     TNT
    0.06
     Clarkson
    0.06
    Act Density 0.002%

    No Known Activations