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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kaf
    -0.07
    Không
    -0.07
    itory
    -0.07
     noct
    -0.06
    itos
    -0.06
    providers
    -0.06
    umi
    -0.06
    替
    -0.06
     incor
    -0.06
    那里
    -0.06
    POSITIVE LOGITS
    _seg
    0.06
     pair
    0.06
    .serialization
    0.06
     coercion
    0.06
     Memory
    0.06
    	Simple
    0.06
    ITIONS
    0.06
    _gb
    0.06
     esteem
    0.06
    kových
    0.06
    Act Density 0.000%

    No Known Activations