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

    Neuronpedia

    INDEX
    Explanations

    weights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solvent
    -0.09
    steam
    -0.08
    Stream
    -0.08
     leisten
    -0.08
     delito
    -0.08
     genus
    -0.08
     stream
    -0.08
     solvents
    -0.07
     paradox
    -0.07
    stream
    -0.07
    POSITIVE LOGITS
    .weights
    0.14
     weights
    0.12
    (weights
    0.12
    _weights
    0.11
     coefficients
    0.11
    weights
    0.11
     коэффици
    0.10
    Weights
    0.10
     coeff
    0.10
    coeff
    0.09
    Act Density 0.006%

    No Known Activations