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

    Neuronpedia

    INDEX
    Explanations

    preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     könnte
    -0.09
    urar
    -0.08
    och
    -0.08
    iciones
    -0.07
    style
    -0.07
    :key
    -0.07
     peso
    -0.07
     ypos
    -0.07
    uch
    -0.07
     metast
    -0.06
    POSITIVE LOGITS
    812
    0.06
     StringBuilder
    0.06
     대상
    0.06
    ят
    0.05
    .")]↵
    0.05
     female
    0.05
    тия
    0.05
    열
    0.05
    .VisualStudio
    0.05
    .getInput
    0.05
    Act Density 0.004%

    No Known Activations