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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ριο
    -0.07
    	card
    -0.07
     Superman
    -0.07
    _pkg
    -0.07
    �
    -0.06
    rt
    -0.06
     Running
    -0.06
     subt
    -0.06
    NSURLSession
    -0.06
    Smarty
    -0.06
    POSITIVE LOGITS
     algún
    0.06
    scious
    0.06
    cısı
    0.06
     peč
    0.06
     Sudan
    0.06
     Lahore
    0.06
    lerinin
    0.06
     *}
    0.06
     Moff
    0.05
    ->$
    0.05
    Act Density 0.063%

    No Known Activations