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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ronald
    -0.07
     warmly
    -0.06
     down
    -0.06
     Abuse
    -0.06
    lectual
    -0.06
     게시판
    -0.06
     classes
    -0.06
    らしい
    -0.06
     entries
    -0.06
     shitty
    -0.05
    POSITIVE LOGITS
    .Sc
    0.06
    &lt
    0.06
    665
    0.06
    
    0.06
    _Size
    0.06
    quina
    0.06
    [ch
    0.06
    К
    0.06
    declare
    0.06
    TO
    0.06
    Act Density 0.000%

    No Known Activations