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

    Neuronpedia

    INDEX
    Explanations

    lists: table, feature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elegantes
    0.44
     largas
    0.44
    OMI
    0.43
     Осо
    0.41
    ТА
    0.41
     húmed
    0.41
     interse
    0.40
     compactly
    0.40
     intelligently
    0.40
     inse
    0.40
    POSITIVE LOGITS
    í
    0.46
     ముందు
    0.44
     راہ
    0.44
    listener
    0.43
    _
    0.43
     Check
    0.41
    ide
    0.41
    tronic
    0.41
    ye
    0.40
    uf
    0.40
    Act Density 0.005%

    No Known Activations