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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    culas
    -0.09
    ul
    -0.08
     মামলা
    -0.08
    strike
    -0.08
    atiiv
    -0.08
    iliar
    -0.07
     mainstream
    -0.07
     piercing
    -0.07
     Mehrheit
    -0.07
     মাম
    -0.07
    POSITIVE LOGITS
     epochs
    0.12
     gedurende
    0.11
    epochs
    0.11
    _epochs
    0.11
    .history
    0.10
    _epoch
    0.10
     Plot
    0.10
     दौरान
    0.10
     трен
    0.10
     epoch
    0.10
    Act Density 0.003%

    No Known Activations