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

    Neuronpedia

    INDEX
    Explanations

    knows you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    фіка
    0.50
    靂
    0.47
    beet
    0.46
    gum
    0.46
     ठो
    0.45
    gly
    0.45
    immel
    0.44
     більш
    0.44
    Ivy
    0.44
    櫚
    0.43
    POSITIVE LOGITS
     concur
    0.54
     keenly
    0.52
     familiar
    0.49
    ונה
    0.47
     craz
    0.46
     drawRight
    0.46
     bank
    0.46
    ვა
    0.45
     razon
    0.45
     inex
    0.45
    Act Density 0.000%

    No Known Activations