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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rubin
    -0.07
    ्रण
    -0.06
     눈을
    -0.06
    lessly
    -0.06
     ///<
    -0.06
    resa
    -0.06
    (Screen
    -0.06
    .allocate
    -0.06
    Stra
    -0.06
     QStringLiteral
    -0.06
    POSITIVE LOGITS
    	value
    0.07
    manager
    0.07
    athlete
    0.06
     inaugural
    0.06
    fout
    0.06
    Helper
    0.06
     dd
    0.06
    (spec
    0.06
     GG
    0.06
    迫
    0.06
    Act Density 0.021%

    No Known Activations