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

    Neuronpedia

    INDEX
    Explanations

    markdown formatting delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esfor
    0.41
    deen
    0.41
    しまい
    0.38
     negócio
    0.37
     Efforts
    0.37
    తన
    0.37
     Craven
    0.37
    しか
    0.37
     کوشش
    0.36
    ਸ
    0.36
    POSITIVE LOGITS
     signifies
    0.42
    最后的
    0.41
     ventaja
    0.39
    的选择
    0.37
     Pfer
    0.36
     betekent
    0.36
     symbolizes
    0.36
     সাধারণত
    0.35
    最後の
    0.35
     *}
    0.35
    Act Density 0.244%

    No Known Activations