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

    Neuronpedia

    INDEX
    Explanations

    key in a dictionary or map

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    0.68
     Phật
    0.66
     abhid
    0.65
    aros
    0.65
    ísmo
    0.65
    arina
    0.64
    Streams
    0.63
    FRINGEMENT
    0.63
     Barrios
    0.63
    ，
    0.63
    POSITIVE LOGITS
    お
    0.75
     have
    0.70
    も
    0.70
     در
    0.66
    の両
    0.63
    ৫
    0.63
     été
    0.63
     és
    0.62
     dessen
    0.62
     gestire
    0.62
    Act Density 0.002%

    No Known Activations