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

    Neuronpedia

    INDEX
    Explanations

    purpose or benefit after "for"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    2.08
    O
    1.53
    I
    1.46
    D
    1.20
    em
    1.16
    S
    1.15
    K
    1.13
    B
    1.12
    G
    1.04
    inį
    1.01
    POSITIVE LOGITS
    ע
    1.37
    ку
    1.08
    lt
    1.04
    0.98
    ни
    0.94
    rt
    0.92
    지
    0.90
    cc
    0.89
    la
    0.88
     be
    0.88
    Act Density 0.634%

    No Known Activations