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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ourselves
    -0.95
     our
    -0.78
     we
    -0.74
     우리
    -0.63
     nostro
    -0.62
     máme
    -0.62
     notre
    -0.62
    Our
    -0.61
     avons
    -0.60
    我们
    -0.59
    POSITIVE LOGITS
     виправивши
    0.87
     souls
    0.85
    ſelf
    0.84
    RenderAtEndOf
    0.84
    SharedCtor
    0.82
    felves
    0.82
    oredCriteria
    0.80
     skulls
    0.78
     yourselves
    0.75
    +:+
    0.73
    Act Density 0.001%

    No Known Activations