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

    Neuronpedia

    INDEX
    Explanations

    experiments and injections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Champ
    -0.07
    ading
    -0.06
     incarceration
    -0.06
     içinde
    -0.06
    ntity
    -0.06
    )Math
    -0.06
    카
    -0.06
     Stap
    -0.06
    โลก
    -0.06
     CompletableFuture
    -0.06
    POSITIVE LOGITS
     letting
    0.07
     knit
    0.07
     seksi
    0.07
     bunk
    0.06
     Throw
    0.06
     MEMBER
    0.06
    Curr
    0.06
    stem
    0.06
    된
    0.06
     Stub
    0.06
    Act Density 0.038%

    No Known Activations