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

    Neuronpedia

    INDEX
    Explanations

    ethical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flies
    -0.07
     imaginative
    -0.06
     للح
    -0.06
    AspectRatio
    -0.06
    ceb
    -0.06
    mf
    -0.06
     fragile
    -0.06
    _embeddings
    -0.06
     apoptosis
    -0.06
    .tar
    -0.06
    POSITIVE LOGITS
    nick
    0.07
     siblings
    0.06
    _workflow
    0.06
    0.06
     фин
    0.06
    _em
    0.06
     noss
    0.06
    METHOD
    0.06
     shipped
    0.06
    .....
    0.06
    Act Density 0.009%

    No Known Activations