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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HashMap
    -0.06
    >r
    -0.06
    ’autres
    -0.06
    bv
    -0.06
    Kitchen
    -0.06
    (Output
    -0.06
     disabilities
    -0.06
     quieres
    -0.06
    schedule
    -0.06
     другие
    -0.06
    POSITIVE LOGITS
     incid
    0.07
     endorsing
    0.07
     đào
    0.07
     Sox
    0.07
     sing
    0.06
     hairstyles
    0.06
     yelled
    0.06
     crackers
    0.06
     motiv
    0.06
     rotations
    0.06
    Act Density 0.037%

    No Known Activations