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

    Neuronpedia

    INDEX
    Explanations

    single-digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mechanical
    -0.07
    .mutable
    -0.06
    :auto
    -0.06
     alumni
    -0.06
     wonderfully
    -0.06
    can
    -0.06
     perpetrators
    -0.06
     booze
    -0.06
    col
    -0.06
    ula
    -0.06
    POSITIVE LOGITS
    ANDING
    0.07
    년
    0.06
    !");↵
    0.06
    режд
    0.06
    ]/
    0.06
    ５
    0.06
     říj
    0.06
    "]));↵
    0.06
     Comic
    0.06
     pregnancies
    0.06
    Act Density 0.016%

    No Known Activations