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

    Neuronpedia

    INDEX
    Explanations

    solutions and problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     damaging
    -0.07
     शत
    -0.07
     Alma
    -0.06
    (pic
    -0.06
    (Target
    -0.06
    )|(
    -0.06
    ربع
    -0.06
    (vol
    -0.06
    適用
    -0.06
     Salah
    -0.06
    POSITIVE LOGITS
    워
    0.07
    .abort
    0.06
    atories
    0.06
    ोन
    0.06
     survivor
    0.06
    扶
    0.06
    Angles
    0.06
     선
    0.06
    elerden
    0.06
    _wave
    0.06
    Act Density 0.058%

    No Known Activations