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

    Neuronpedia

    INDEX
    Explanations

    Boxing knockdowns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verty
    -0.08
    find
    -0.07
    UIScrollView
    -0.07
    Thank
    -0.07
    ksam
    -0.07
     smirk
    -0.07
    おそ
    -0.07
    ..<
    -0.07
     terrorist
    -0.07
    знак
    -0.07
    POSITIVE LOGITS
     slower
    0.08
     halten
    0.07
    ")));↵
    0.07
     FR
    0.07
     WHERE
    0.07
    _food
    0.06
    Ở
    0.06
     czy
    0.06
    .lang
    0.06
    0.06
    Act Density 0.005%

    No Known Activations