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

    Neuronpedia

    INDEX
    Explanations

    highly + descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     high
    1.01
    high
    1.00
    High
    0.97
    ately
    0.95
     forze
    0.89
     High
    0.88
     heights
    0.86
    高
    0.85
    height
    0.85
    nią
    0.83
    POSITIVE LOGITS
     individual
    0.86
     macrophage
    0.78
    individual
    0.77
     Individual
    0.76
    acres
    0.76
     elliptical
    0.74
    Individual
    0.73
    arden
    0.72
     প্রশংসা
    0.72
     selectively
    0.72
    Act Density 0.067%

    No Known Activations