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

    Neuronpedia

    INDEX
    Explanations

    chain of thought and reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    debug
    0.82
    RE
    0.79
    ef
    0.76
    ent
    0.75
    ai
    0.74
    forRoot
    0.73
    aires
    0.73
    Interfaz
    0.72
    color
    0.72
    cores
    0.71
    POSITIVE LOGITS
     قد
    0.80
     excruciating
    0.77
     suspicions
    0.77
     appalling
    0.74
     mysteriously
    0.74
    隰
    0.74
     ominous
    0.74
     stinging
    0.74
     implication
    0.73
     Та
    0.73
    Act Density 0.004%

    No Known Activations