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

    Neuronpedia

    INDEX
    Explanations

    into sections or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.55
    }$
    2.13
    ्स
    1.89
    g
    1.80
    ’
    1.76
    ਰ
    1.74
    }]$
    1.73
    }%
    1.67
    }))
    1.67
    nap
    1.66
    POSITIVE LOGITS
    ש
    2.16
    த்
    2.08
    ला
    1.92
     perpetuity
    1.91
    čna
    1.88
    ция
    1.88
    čnom
    1.85
    čiti
    1.84
    ğini
    1.83
    ە
    1.82
    Act Density 0.153%

    No Known Activations