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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    デ
    -0.06
     своб
    -0.06
    ْم
    -0.06
     člověk
    -0.06
     pisc
    -0.06
     nf
    -0.06
     Orchard
    -0.06
    ộc
    -0.06
     사라
    -0.06
     kms
    -0.06
    POSITIVE LOGITS
    gender
    0.07
    $_
    0.07
     transgender
    0.07
    是
    0.07
    omers
    0.06
     Highlands
    0.06
    croll
    0.06
     Transportation
    0.06
    共
    0.06
     scout
    0.06
    Act Density 0.001%

    No Known Activations