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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卓
    -0.07
     Kills
    -0.07
    ypical
    -0.07
    드리
    -0.07
     тогда
    -0.07
    пис
    -0.06
    ्थन
    -0.06
    �
    -0.06
     dobře
    -0.06
    Nullable
    -0.06
    POSITIVE LOGITS
     Ort
    0.07
     SEL
    0.07
    Sig
    0.07
     trục
    0.06
     gum
    0.06
     Ley
    0.06
     //</
    0.06
    inja
    0.06
     milliseconds
    0.06
    `↵↵
    0.06
    Act Density 0.000%

    No Known Activations