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

    Neuronpedia

    INDEX
    Explanations

    non-standard characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.97
    dt
    0.94
    rt
    0.92
    ût
    0.90
    ln
    0.84
    RT
    0.82
    ld
    0.78
    lt
    0.78
    bt
    0.77
    od
    0.77
    POSITIVE LOGITS
    "
    1.01
     "|"
    1.01
     emoji
    0.95
    "@
    0.93
     "#
    0.93
     histogram
    0.93
     cusp
    0.93
     graf
    0.92
     activ
    0.92
     cli
    0.92
    Act Density 0.000%

    No Known Activations