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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     did
    -0.08
    ㎥
    -0.07
     du
    -0.07
    _Port
    -0.07
     further
    -0.07
    	void
    -0.07
     Often
    -0.07
    (Index
    -0.07
     sito
    -0.06
    “And
    -0.06
    POSITIVE LOGITS
     сах
    0.08
     unilateral
    0.07
    チョ
    0.07
    Royal
    0.07
    gran
    0.07
    葺
    0.06
    悅
    0.06
     каз
    0.06
    о�
    0.06
    bab
    0.06
    Act Density 0.036%

    No Known Activations