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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    schools
    -0.07
    �
    -0.07
    _ORIGIN
    -0.07
    ُّ
    -0.06
     rdf
    -0.06
     اتفاق
    -0.06
    nar
    -0.06
    acf
    -0.06
    чет
    -0.06
     надання
    -0.06
    POSITIVE LOGITS
     nach
    0.07
    .dim
    0.07
     روی
    0.07
     payoff
    0.06
    .less
    0.06
    iams
    0.06
     tumor
    0.06
     prost
    0.06
     paren
    0.06
     Bash
    0.06
    Act Density 0.021%

    No Known Activations