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

    Neuronpedia

    INDEX
    Explanations

    quantities or states with options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.46
    Hour
    0.45
    Impact
    0.45
    Dent
    0.44
     момент
    0.44
    Á
    0.44
    Entity
    0.43
    O
    0.43
    Side
    0.42
    本文
    0.41
    POSITIVE LOGITS
     juggle
    0.57
    jew
    0.49
     accurately
    0.48
     regl
    0.47
     Westwood
    0.46
     estrellas
    0.45
    ેલ
    0.44
    inare
    0.44
    ktor
    0.44
     arena
    0.44
    Act Density 0.002%

    No Known Activations