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

    Neuronpedia

    INDEX
    Explanations

    bib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	global
    -0.07
     graft
    -0.07
    ुआ
    -0.06
     TIMEOUT
    -0.06
     clashes
    -0.06
    روط
    -0.06
    .direction
    -0.06
     blind
    -0.06
     первую
    -0.06
    .bl
    -0.06
    POSITIVE LOGITS
     Rings
    0.06
    058
    0.06
     Epidemi
    0.06
    reira
    0.06
    ي
    0.06
     Owners
    0.06
    ativos
    0.06
    couldn
    0.06
     calculus
    0.06
    .');
↵
    0.06
    Act Density 0.002%

    No Known Activations