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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiment/strong opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ภาษ
    -0.07
     Progressive
    -0.07
     رس
    -0.07
     escal
    -0.06
     bufsize
    -0.06
    ‡
    -0.06
     transmit
    -0.06
    /Admin
    -0.06
    .Background
    -0.06
     Lust
    -0.06
    POSITIVE LOGITS
     IOCTL
    0.08
     darüber
    0.06
    :both
    0.06
    ({},
    0.06
     kvinnor
    0.06
     drown
    0.06
    ;?>"
    0.06
    .isBlank
    0.06
    (password
    0.06
    iệ
    0.06
    Act Density 0.180%

    No Known Activations