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

    Neuronpedia

    INDEX
    Explanations

    clickbait

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _wf
    -0.07
    administr
    -0.07
    .getOwnProperty
    -0.07
    抨
    -0.06
     위해
    -0.06
    (Print
    -0.06
    _##
    -0.06
    umo
    -0.06
    FINAL
    -0.06
    more
    -0.06
    POSITIVE LOGITS
    Whilst
    0.07
     bush
    0.07
     Boundary
    0.07
    多年前
    0.07
    brush
    0.07
     rotations
    0.07
    Ha
    0.07
    ?key
    0.07
     alters
    0.07
     Daisy
    0.06
    Act Density 0.017%

    No Known Activations