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

    Neuronpedia

    INDEX
    Explanations

    Scientific comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mc
    -0.07
     Lud
    -0.06
     Ingram
    -0.06
    ']").
    -0.06
    рим
    -0.06
     '}
    -0.06
    etails
    -0.06
    もない
    -0.06
     вд
    -0.06
     mücadel
    -0.06
    POSITIVE LOGITS
    Continue
    0.08
     INTERFACE
    0.06
     bonus
    0.06
     NotFound
    0.06
    (hero
    0.06
    paired
    0.06
     chinese
    0.06
     withdrew
    0.06
    .cookies
    0.06
     BLL
    0.06
    Act Density 0.022%

    No Known Activations