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

    Neuronpedia

    INDEX
    Explanations

    Ice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bootstrap
    -0.08
    -tooltip
    -0.07
     гум
    -0.06
    ?>">
    -0.06
     agar
    -0.06
    руп
    -0.06
    (calendar
    -0.06
     Handler
    -0.06
    	hs
    -0.06
    fails
    -0.06
    POSITIVE LOGITS
     Violence
    0.07
    rends
    0.06
    侵
    0.06
     Abram
    0.06
     движ
    0.06
    izzly
    0.06
     prázd
    0.06
     LOS
    0.06
     욕
    0.06
    ائب
    0.06
    Act Density 0.001%

    No Known Activations