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

    Neuronpedia

    INDEX
    Explanations

    incoherent text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Component
    -0.07
    (lbl
    -0.06
    )))↵↵↵
    -0.06
     보내
    -0.06
    ılıp
    -0.06
     Α
    -0.06
     idade
    -0.06
     کیلومتر
    -0.06
     симптом
    -0.06
     Personnel
    -0.06
    POSITIVE LOGITS
    GREEN
    0.07
    єм
    0.07
    ictions
    0.07
     Sentry
    0.07
    iving
    0.07
     Rough
    0.07
    IVING
    0.07
    Ordered
    0.07
    HOST
    0.06
    _groups
    0.06
    Act Density 0.004%

    No Known Activations