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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mamış
    -0.07
    шается
    -0.06
     evacuated
    -0.06
     sessions
    -0.06
    CodeGen
    -0.06
     meteor
    -0.06
     hath
    -0.06
     stories
    -0.06
    нка
    -0.06
    เง
    -0.06
    POSITIVE LOGITS
     Wisconsin
    0.07
     очист
    0.07
    /↵↵
    0.06
    candidate
    0.06
    654
    0.06
    $↵↵
    0.06
     del
    0.06
     candidate
    0.06
     LOS
    0.06
    ################################################################
    0.06
    Act Density 0.000%

    No Known Activations