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

    Neuronpedia

    INDEX
    Explanations

    code and logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沃
    -0.09
    	target
    -0.08
    	next
    -0.08
    ვ
    -0.07
     nor
    -0.07
     reservoir
    -0.07
     pore
    -0.07
     willing
    -0.07
     shore
    -0.07
    ользоват
    -0.07
    POSITIVE LOGITS
     fetisch
    0.08
    褙
    0.07
     //{
↵
    0.07
    _icall
    0.07
     מדה
    0.07
    🌽
    0.07
    โคร
    0.07
     JNICALL
    0.07
    }()↵↵
    0.07
    みると
    0.06
    Act Density 0.061%

    No Known Activations