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

    Neuronpedia

    INDEX
    Explanations

    rp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ním
    -0.07
     urban
    -0.06
    Delta
    -0.06
     yeterli
    -0.06
    /document
    -0.06
     dne
    -0.06
     moż
    -0.06
     dile
    -0.06
     będzie
    -0.06
    ้อย
    -0.06
    POSITIVE LOGITS
    สอง
    0.06
    blur
    0.06
     rally
    0.06
     Mothers
    0.06
    ters
    0.06
    semicolon
    0.06
     THREE
    0.06
     Fighter
    0.06
     scala
    0.06
    oggler
    0.06
    Act Density 0.007%

    No Known Activations