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

    Neuronpedia

    INDEX
    Explanations

    egg came first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    0.53
    ene
    0.53
    ine
    0.51
    ge
    0.51
    ang
    0.50
    are
    0.49
    ree
    0.48
    eg
    0.47
    sono
    0.47
    is
    0.46
    POSITIVE LOGITS
     nguyện
    0.44
     ylab
    0.44
     iniciativas
    0.43
     hábitos
    0.42
     relatable
    0.42
    기와
    0.42
     getUsersBy
    0.41
     saudável
    0.41
     sciatica
    0.41
     tiên
    0.41
    Act Density 0.007%

    No Known Activations