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

    Neuronpedia

    INDEX
    Explanations

    category numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉపయోగ
    0.25
     شما
    0.24
    㚼
    0.23
     आपण
    0.22
    MovementControls
    0.22
     ㅛ
    0.22
    MatContext
    0.22
     〢
    0.22
    thisTrack
    0.22
     یقین
    0.22
    POSITIVE LOGITS
    i
    0.41
    k
    0.36
    z
    0.36
    d
    0.35
    g
    0.32
    c
    0.31
    p
    0.31
    u
    0.30
    b
    0.30
    x
    0.30
    Act Density 0.467%

    No Known Activations