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

    Neuronpedia

    INDEX
    Explanations

    he was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Worse
    0.75
     whence
    0.69
     Maybe
    0.68
     necessitating
    0.67
     assurances
    0.64
    そういう
    0.64
     cursory
    0.64
     đấy
    0.64
    Maybe
    0.63
     somebody
    0.63
    POSITIVE LOGITS
    bst
    0.91
     samsung
    0.88
    orption
    0.86
    ron
    0.86
     стрельца
    0.85
    propane
    0.85
     নির্যাতন
    0.84
    amese
    0.84
    ovolta
    0.84
     shakespeare
    0.84
    Act Density 0.009%

    No Known Activations