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

    Neuronpedia

    INDEX
    Explanations

    informal discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annis
    -0.07
    ався
    -0.06
     Total
    -0.06
    ("")
    -0.06
     Early
    -0.06
     probabil
    -0.06
     Randolph
    -0.05
    मर
    -0.05
     thunder
    -0.05
     jointly
    -0.05
    POSITIVE LOGITS
    pagination
    0.08
    .lineWidth
    0.07
    (Qt
    0.07
    чук
    0.07
     وان
    0.07
     )↵↵↵↵↵↵↵↵
    0.07
    GetEnumerator
    0.07
    	TokenNameIdentifier
    0.07
     odpověd
    0.06
     ■
    0.06
    Act Density 0.053%

    No Known Activations