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

    Neuronpedia

    INDEX
    Explanations

    punctuation and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.75
    *
    0.72
     અને
    0.69
    amek
    0.69
    INNER
    0.66
    }+\
    0.66
    τητα
    0.65
    Με
    0.64
    ية
    0.64
    }}>
    0.64
    POSITIVE LOGITS
     VoIP
    0.91
     Walgreens
    0.89
    čas
    0.86
     Sega
    0.86
     Corps
    0.82
     Redmi
    0.82
     Yahoo
    0.82
     Yunnan
    0.81
     paintball
    0.81
     humane
    0.80
    Act Density 0.001%

    No Known Activations