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

    Neuronpedia

    INDEX
    Explanations

    app development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    slightly
    0.54
    assume
    0.48
    s
    0.46
    some
    0.46
    eu
    0.45
     liht
    0.45
    sst
    0.44
     légèrement
    0.44
    det
    0.43
     slightly
    0.42
    POSITIVE LOGITS
     Worked
    0.43
     groundwork
    0.42
     Chromatography
    0.41
     वाजिब
    0.40
     unprecedented
    0.39
    Worked
    0.39
    धारकों
    0.37
    対訳
    0.37
    ख्त
    0.36
     Mixing
    0.36
    Act Density 0.000%

    No Known Activations