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

    Neuronpedia

    INDEX
    Explanations

    anthocyanins and NAACP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    1.11
    ton
    1.02
     on
    0.93
     sanit
    0.91
     synchron
    0.82
     deň
    0.82
    ther
    0.82
    ర్థిక
    0.79
    rik
    0.78
    </
    0.78
    POSITIVE LOGITS
    को
    1.05
    та
    0.99
    나
    0.93
    ST
    0.93
    다
    0.93
    ਾ
    0.93
    א
    0.88
    ،
    0.86
    Setelah
    0.86
     appetizers
    0.86
    Act Density 0.001%

    No Known Activations