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

    Neuronpedia

    INDEX
    Explanations

    punctuation and common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kitchen
    0.47
    воз
    0.43
     обуча
    0.43
    }$
    0.42
     sparse
    0.42
     персонала
    0.42
    }$,
    0.41
     kitchen
    0.41
    var
    0.40
     zich
    0.40
    POSITIVE LOGITS
    িয়ন
    0.51
     ಸ್ಥ
    0.49
    唂
    0.47
    चर्स
    0.46
    namento
    0.45
    inę
    0.44
     neoplas
    0.43
     দুর
    0.43
     tajem
    0.43
    нення
    0.43
    Act Density 0.000%

    No Known Activations