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

    Neuronpedia

    INDEX
    Explanations

    "rescue"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fdata
    1.09
     achie
    1.08
     bueno
    1.08
     acceptability
    1.07
    しっかり
    1.03
     ahi
    1.03
    基于
    1.01
    ative
    1.00
     integ
    1.00
     enrich
    1.00
    POSITIVE LOGITS
    ्स
    1.01
    $
    0.94
     landslide
    0.92
     besieged
    0.86
    $+
    0.84
     目前
    0.82
    ی
    0.82
    $$
    0.81
     twice
    0.79
    counting
    0.79
    Act Density 0.000%

    No Known Activations