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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /embed
    -0.07
     histoire
    -0.07
     nivel
    -0.07
     participating
    -0.07
    _DEN
    -0.07
    _CUR
    -0.06
     codecs
    -0.06
    流れ
    -0.06
    tickets
    -0.06
     dude
    -0.06
    POSITIVE LOGITS
     Па
    0.07
    	the
    0.07
    螬
    0.07
    pei
    0.07
    耐用
    0.07
     sucess
    0.07
     laptop
    0.07
     @{$
    0.07
     Alb
    0.06
    理工
    0.06
    Act Density 0.008%

    No Known Activations