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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ून
    -0.07
    ı
    -0.07
     Наг
    -0.07
     timp
    -0.07
    [of
    -0.07
    pants
    -0.07
    нам
    -0.07
     본
    -0.07
     trophy
    -0.06
    POSITIVE LOGITS
     místní
    0.06
    	parse
    0.06
     Generally
    0.06
    urtles
    0.06
    .OPEN
    0.06
    effective
    0.06
     gunfire
    0.06
    lectron
    0.06
    Generally
    0.06
    .answers
    0.06
    Act Density 0.000%

    No Known Activations