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

    Neuronpedia

    INDEX
    Explanations

    plut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Activation
    -0.06
     лі
    -0.06
    .models
    -0.06
     aber
    -0.06
    )">
    -0.06
    DELAY
    -0.06
     racing
    -0.06
    \Models
    -0.06
     double
    -0.06
     ول
    -0.06
    POSITIVE LOGITS
     plut
    0.09
     CORE
    0.06
    _regex
    0.06
     militia
    0.06
    nova
    0.06
     سكان
    0.06
    lady
    0.06
    hydr
    0.06
    mit
    0.06
    Ex
    0.06
    Act Density 0.001%

    No Known Activations