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

    Neuronpedia

    INDEX
    Explanations

    novel accounting actions yield motivation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    0.72
    T
    0.55
    CAS
    0.55
    L
    0.53
    J
    0.51
    R
    0.50
    H
    0.50
    X
    0.49
    I
    0.49
    B
    0.48
    POSITIVE LOGITS
     นั่น
    0.50
     matem
    0.49
     поса
    0.49
     optical
    0.46
     भरे
    0.46
    duration
    0.46
     मात्रा
    0.46
     minuti
    0.46
     dür
    0.45
    کیا
    0.45
    Act Density 0.001%

    No Known Activations