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

    Neuronpedia

    INDEX
    Explanations

    When

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pr
    -0.07
     Composite
    -0.06
     Facility
    -0.06
    .When
    -0.06
     dán
    -0.06
    flen
    -0.06
    _geo
    -0.06
    吴
    -0.06
    .cz
    -0.06
     \↵↵
    -0.06
    POSITIVE LOGITS
     habe
    0.06
     العم
    0.06
    _ir
    0.06
    (program
    0.06
    	dp
    0.06
    buzz
    0.06
    لان
    0.06
    арт
    0.06
     Serve
    0.06
     Rei
    0.06
    Act Density 0.052%

    No Known Activations