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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sound
    -0.07
     waived
    -0.07
     longstanding
    -0.07
     folly
    -0.06
     wei
    -0.06
     bringen
    -0.06
    -radio
    -0.06
    خاب
    -0.06
     cómo
    -0.06
    radan
    -0.06
    POSITIVE LOGITS
     Dich
    0.06
    εδ
    0.06
    {
↵
    0.06
     TInt
    0.06
    uc
    0.06
    (argc
    0.06
    ="#
    0.06
     테
    0.06
    LineStyle
    0.06
    áci
    0.06
    Act Density 0.001%

    No Known Activations