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

    Neuronpedia

    INDEX
    Explanations

    step number or sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    engesellschaft
    0.64
    ...(
    0.63
     Honors
    0.61
    col
    0.61
    ütter
    0.61
    ंदगी
    0.61
    ...
    0.60
    ("
    0.60
     **
    0.60
    **(
    0.60
    POSITIVE LOGITS
     Following
    0.88
    chmod
    0.79
     nakon
    0.78
     Thereafter
    0.75
     thereafter
    0.74
     setelah
    0.73
     Configure
    0.73
     після
    0.73
     After
    0.71
     Given
    0.71
    Act Density 0.084%

    No Known Activations