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

    Neuronpedia

    INDEX
    Explanations

    Competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    钻研
    -0.08
    (ticket
    -0.08
    Pixmap
    -0.07
    _SIGNATURE
    -0.07
    adj
    -0.07
     Jens
    -0.07
    Extensions
    -0.07
    _before
    -0.07
    百余
    -0.07
    AuthGuard
    -0.07
    POSITIVE LOGITS
    饿
    0.07
    0.07
    .")
↵
    0.07
     chemical
    0.07
    polation
    0.07
     时间
    0.06
    0.06
    会在
    0.06
    .jet
    0.06
     Eva
    0.06
    Act Density 0.031%

    No Known Activations