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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Amb
    -0.07
    ，说
    -0.06
    pii
    -0.06
    Metro
    -0.06
    ูก
    -0.06
    Songs
    -0.06
    中央
    -0.06
     Maggie
    -0.06
    administrator
    -0.06
     formerly
    -0.06
    POSITIVE LOGITS
    "context
    0.07
    (units
    0.07
     proclamation
    0.07
     strokeLine
    0.07
    ансов
    0.07
    页
    0.07
    .WriteAllText
    0.07
    	assertEquals
    0.06
     Foam
    0.06
    ="${
    0.06
    Act Density 0.138%

    No Known Activations