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

    Neuronpedia

    INDEX
    Explanations

    C++ std:: usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    穣
    0.30
    ROLL
    0.25
     اکت
    0.25
     orchards
    0.25
     POSSIBLE
    0.25
     COUNCIL
    0.24
     細胞
    0.24
    ulins
    0.24
     McPherson
    0.24
    UNDO
    0.24
    POSITIVE LOGITS
    without
    0.30
     Ez
    0.30
    With
    0.30
    with
    0.28
     With
    0.28
     Without
    0.28
    value
    0.27
    getValue
    0.27
    in
    0.27
     without
    0.26
    Act Density 0.000%

    No Known Activations