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

    Neuronpedia

    INDEX
    Explanations

    say "ville"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disclosed
    -0.06
     discovery
    -0.06
    transform
    -0.06
     rushed
    -0.06
    “你
    -0.06
     grinned
    -0.06
     insects
    -0.06
     sparking
    -0.06
     döndü
    -0.06
     tapping
    -0.06
    POSITIVE LOGITS
    .getValue
    0.08
     Remain
    0.07
     fidelity
    0.07
    ế
    0.07
    _ability
    0.07
    issippi
    0.07
     Giám
    0.06
     SKIP
    0.06
    lege
    0.06
    _MOBILE
    0.06
    Act Density 0.001%

    No Known Activations