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

    Neuronpedia

    INDEX
    Explanations

    cybersecurity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sprite
    -0.08
    网址
    -0.08
    _rgb
    -0.08
    suffix
    -0.08
    _density
    -0.08
    _sprite
    -0.07
     rhoi
    -0.07
    (pub
    -0.07
    isty
    -0.07
     jste
    -0.07
    POSITIVE LOGITS
     Trusted
    0.10
    Trusted
    0.09
     blinds
    0.09
    ತನ
    0.08
     Assignment
    0.08
    .Duration
    0.08
    .Hour
    0.08
     afer
    0.08
     SDR
    0.07
    .Unknown
    0.07
    Act Density 0.001%

    No Known Activations