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

    Neuronpedia

    INDEX
    Explanations

    Consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roots
    -0.08
    _strength
    -0.07
    OL
    -0.07
    torrent
    -0.07
     fld
    -0.07
    -review
    -0.07
    YL
    -0.07
     pipes
    -0.06
     cuts
    -0.06
    วด
    -0.06
    POSITIVE LOGITS
     unheard
    0.07
    enate
    0.07
    ême
    0.07
     합
    0.06
    Fecha
    0.06
    ocommerce
    0.06
     locker
    0.06
     comme
    0.06
     BAŞ
    0.06
     Krist
    0.06
    Act Density 0.016%

    No Known Activations