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

    Neuronpedia

    INDEX
    Explanations

    money amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    刺繍
    0.77
    сь
    0.76
    កម្ម
    0.75
    ខ្ញ
    0.75
     但
    0.74
    ない
    0.73
    ᅴ
    0.73
    Exists
    0.71
    ун
    0.71
     coursework
    0.71
    POSITIVE LOGITS
     });
    0.62
     }=
    0.62
    </strong>
    0.61
    </h4>
    0.60
    תוך
    0.60
     }=\
    0.59
    foreground
    0.59
    tract
    0.56
    Calls
    0.56
    )}(\
    0.55
    Act Density 0.001%

    No Known Activations