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

    Neuronpedia

    INDEX
    Explanations

    page numbers or ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.70
     desperate
    0.69
     pre
    0.66
     live
    0.61
     unleash
    0.60
     tuto
    0.60
     powerful
    0.59
     or
    0.59
     desesper
    0.59
     self
    0.59
    POSITIVE LOGITS
    .–
    1.00
    –
    0.91
    .}$
    0.87
    .‏
    0.84
    .].
    0.82
    +.
    0.79
    .-
    0.77
    .).
    0.76
    .}
    0.76
    0.75
    Act Density 0.003%

    No Known Activations