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
     Dry
    -0.07
    mant
    -0.06
    尋
    -0.06
    oncé
    -0.06
    _stand
    -0.06
     umění
    -0.06
    hyp
    -0.06
    ackson
    -0.06
     поскольку
    -0.06
     служби
    -0.06
    POSITIVE LOGITS
     placements
    0.06
     Brisbane
    0.06
     recl
    0.06
    unsqueeze
    0.06
    .ReadOnly
    0.06
    /">
    0.06
     Aust
    0.06
    _DIS
    0.06
     masc
    0.06
     EU
    0.06
    Act Density 0.062%

    No Known Activations