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

    Neuronpedia

    INDEX
    Explanations

    relevant information or criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    2.66
    و
    2.53
    ו
    2.53
    ת
    2.27
    ल
    2.20
    ত্ব
    2.17
    ت
    2.11
    з
    2.11
    ר
    2.09
    ли
    2.02
    POSITIVE LOGITS
    okhlov
    1.45
     uprisings
    1.45
     smears
    1.39
    CodeableConcept
    1.37
    ON
    1.34
    SA
    1.34
    msgs
    1.34
     copyspace
    1.34
    SD
    1.33
    LER
    1.32
    Act Density 0.048%

    No Known Activations