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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.92
    enumii
    -0.84
     ostavi
    -0.82
    UnitTesting
    -0.81
     ejus
    -0.78
    encodeWith
    -0.78
    rentices
    -0.77
     localObject
    -0.77
    GraphicsUnit
    -0.77
    tôi
    -0.77
    POSITIVE LOGITS
    ized
    0.66
    s
    0.59
    ities
    0.55
    ms
    0.54
    ns
    0.53
    ts
    0.53
    ious
    0.50
    sb
    0.49
    ied
    0.49
    sche
    0.48
    Act Density 0.042%

    No Known Activations