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

    Neuronpedia

    INDEX
    Explanations

    learning and testing assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Adap
    0.44
    riele
    0.39
    Phenyl
    0.39
    .
    0.38
    Holmes
    0.37
    Venez
    0.37
    Stefan
    0.37
    yphenyl
    0.36
    esterno
    0.36
     Hond
    0.36
    POSITIVE LOGITS
     quadratic
    0.42
     genetics
    0.41
     assumptions
    0.40
     complexion
    0.40
     values
    0.40
     variables
    0.40
     Assumptions
    0.40
     perceptions
    0.39
     genes
    0.39
     genotypes
    0.39
    Act Density 0.001%

    No Known Activations