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

    Neuronpedia

    INDEX
    Explanations

    character to ascii value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imgInit
    0.38
     punctuation
    0.38
    AAE
    0.36
     विभक्ति
    0.36
    giphy
    0.36
    btc
    0.36
     शता
    0.35
    pinterest
    0.35
    entino
    0.35
     Skyscanner
    0.35
    POSITIVE LOGITS
     weight
    0.44
     forty
    0.37
     prote
    0.37
     forbind
    0.37
     pesos
    0.36
     punya
    0.36
     weights
    0.35
     reden
    0.35
     crisp
    0.34
    offsetTop
    0.34
    Act Density 0.001%

    No Known Activations