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

    Neuronpedia

    INDEX
    Explanations

    all except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bestimmten
    0.43
    cat
    0.41
    ्रेन
    0.38
    alone
    0.38
     suivante
    0.38
     alone
    0.37
     bestimmte
    0.37
     namens
    0.37
    lungen
    0.36
    指定的
    0.36
    POSITIVE LOGITS
     except
    0.66
     kecuali
    0.61
    except
    0.59
     Except
    0.58
     EXCEPT
    0.58
    Except
    0.57
     excepto
    0.54
     sauf
    0.54
    특히
    0.53
    Especially
    0.52
    Act Density 0.079%

    No Known Activations