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

    Neuronpedia

    INDEX
    Explanations

    Medical Devices and backups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.64
     n
    0.57
     in
    0.57
    !
    0.55
    '
    0.54
     E
    0.53
     Anthem
    0.52
     de
    0.52
     quell
    0.52
     P
    0.50
    POSITIVE LOGITS
    TIMESTAMPDIFF
    0.54
     hMut
    0.52
    Kotlin
    0.52
     μαγγ
    0.51
    doFilter
    0.50
     obtenido
    0.50
    bathtub
    0.49
    AGMENT
    0.49
    밂
    0.49
    Unifier
    0.49
    Act Density 0.000%

    No Known Activations