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

    Neuronpedia

    INDEX
    Explanations

    general English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ninja
    -0.06
    @param
    -0.06
    从
    -0.06
    rezent
    -0.06
    從
    -0.06
     böylece
    -0.06
    Gay
    -0.06
     контролю
    -0.06
    ーー
    -0.06
    green
    -0.06
    POSITIVE LOGITS
    soap
    0.07
     teased
    0.06
     Tento
    0.06
     *)((
    0.06
    lectric
    0.06
    arios
    0.06
    γγελ
    0.06
     ori
    0.06
    .this
    0.06
    Q
    0.06
    Act Density 0.000%

    No Known Activations