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
    	part
    -0.08
     paramName
    -0.07
     timestamps
    -0.07
    %
    -0.06
    unistd
    -0.06
    inch
    -0.06
    -One
    -0.06
     \%
    -0.06
    -thumbnails
    -0.06
    _headers
    -0.06
    POSITIVE LOGITS
    θε
    0.06
    一起
    0.06
     남자
    0.06
    기
    0.06
     crossed
    0.06
     визнача
    0.06
    iyim
    0.06
    diler
    0.06
     było
    0.06
    bara
    0.06
    Act Density 0.074%

    No Known Activations