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

    Neuronpedia

    INDEX
    Explanations

    error messages and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नाना
    0.44
    排名
    0.40
    Ne
    0.40
     जलवायु
    0.39
    RAW
    0.38
    Galaxy
    0.38
     Spell
    0.38
    Spell
    0.38
    beiten
    0.37
    HP
    0.37
    POSITIVE LOGITS
     FM
    0.79
     fm
    0.76
     Fm
    0.74
    fm
    0.72
    FM
    0.63
     modulating
    0.54
     synthesizing
    0.54
    Deviation
    0.53
     deviations
    0.52
     deviation
    0.50
    Act Density 0.004%

    No Known Activations