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

    Neuronpedia

    INDEX
    Explanations

    credentials and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wher
    0.54
    ﭼ
    0.50
    নো
    0.50
     extravagant
    0.49
     fale
    0.48
    𝙥
    0.48
    ⑶
    0.48
    Ⲉ
    0.47
    ڠ
    0.46
    0.46
    POSITIVE LOGITS
    ö
    0.48
    Mit
    0.46
    ೂ
    0.46
     ihrer
    0.44
     അരി
    0.44
    uš
    0.44
    ansh
    0.44
     ihre
    0.43
    ü
    0.43
    iaan
    0.43
    Act Density 0.000%

    No Known Activations