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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etr
    -0.07
    orial
    -0.07
    idente
    -0.06
     turmoil
    -0.06
     Cosmetic
    -0.06
    در
    -0.06
     Lynn
    -0.06
    ама
    -0.06
    洲
    -0.06
    ़े
    -0.06
    POSITIVE LOGITS
    @implementation
    0.07
    Depending
    0.06
     ():
    0.06
    „D
    0.06
     ภ
    0.06
    면서
    0.06
    .TrimSpace
    0.06
     Aless
    0.06
    _OBJC
    0.06
    —if
    0.06
    Act Density 0.016%

    No Known Activations