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

    Neuronpedia

    INDEX
    Explanations

    Inspector settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.66
    रा
    0.61
    }\
    0.60
    서
    0.57
    犸
    0.56
    अ
    0.56
    };
    0.54
    उत्तर
    0.54
    וא
    0.54
    RA
    0.53
    POSITIVE LOGITS
     sedentary
    0.85
    𝓵
    0.73
     stunted
    0.68
     sequels
    0.66
    cstdlib
    0.65
     haloes
    0.64
     smugglers
    0.63
     reasons
    0.63
     starve
    0.63
    പടി
    0.63
    Act Density 0.003%

    No Known Activations