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

    Neuronpedia

    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vid
    -0.09
     العم
    -0.08
    常务副
    -0.07
     Viện
    -0.07
    /linux
    -0.07
    航天
    -0.06
    administr
    -0.06
     deciding
    -0.06
    INUX
    -0.06
     финанс
    -0.06
    POSITIVE LOGITS
     altered
    0.07
     destabil
    0.06
    sqrt
    0.06
    窃
    0.06
     Today
    0.06
     squat
    0.06
    .format
    0.06
    產
    0.06
     Раз
    0.06
    ителей
    0.06
    Act Density 0.000%

    No Known Activations