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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    statement
    -0.06
    ographer
    -0.06
     impulses
    -0.06
    AIL
    -0.06
    -category
    -0.06
    VERT
    -0.06
    mak
    -0.06
    nop
    -0.06
     exporter
    -0.06
    会
    -0.06
    POSITIVE LOGITS
     смерти
    0.07
     Česk
    0.07
    �
    0.06
     İŞ
    0.06
    <ll
    0.06
    kerja
    0.06
     выс
    0.06
    [Boolean
    0.06
    車
    0.06
    	sf
    0.06
    Act Density 0.053%

    No Known Activations