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

    Neuronpedia

    INDEX
    Explanations

    military operations and potential risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hypothesize
    0.48
     verbally
    0.48
     creado
    0.47
     essentially
    0.47
     saber
    0.46
     overly
    0.46
     be
    0.44
    ylus
    0.44
     excessively
    0.44
     you
    0.44
    POSITIVE LOGITS
    al
    0.55
    Sport
    0.54
    m
    0.52
    ді
    0.51
    हन
    0.51
    Spectrum
    0.49
    RequestParam
    0.49
    African
    0.48
    Ди
    0.48
    Clusters
    0.48
    Act Density 0.001%

    No Known Activations