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

    Neuronpedia

    INDEX
    Explanations

    conducted by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ко
    0.52
     Seit
    0.49
     Regional
    0.48
    ло
    0.46
     جول
    0.46
     Dryden
    0.46
    殿
    0.45
    мах
    0.44
     Umgang
    0.44
    的态度
    0.43
    POSITIVE LOGITS
     scars
    0.52
     outros
    0.51
    olutions
    0.49
    𝔬
    0.48
     malls
    0.47
     surprises
    0.47
     profits
    0.47
     ottim
    0.47
     radiographs
    0.47
     audits
    0.46
    Act Density 0.000%

    No Known Activations