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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Feb
    -0.07
    orro
    -0.06
    Began
    -0.06
     chase
    -0.06
     communicating
    -0.06
    BERT
    -0.06
    ότε
    -0.06
     Lists
    -0.06
    _LEFT
    -0.06
    stories
    -0.06
    POSITIVE LOGITS
     getPassword
    0.07
    	↵	↵
    0.07
    ologne
    0.07
    のみ
    0.07
    ीश
    0.07
    	select
    0.06
     stě
    0.06
    .backup
    0.06
     unlock
    0.06
    _REALTYPE
    0.06
    Act Density 0.000%

    No Known Activations