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

    Neuronpedia

    INDEX
    Explanations

    Ibn names, ganache, plenitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Neck
    0.71
     Lit
    0.70
     Challenge
    0.69
    ડ
    0.67
     lit
    0.66
     impersonal
    0.66
     desafíos
    0.66
     challenging
    0.65
     interventions
    0.65
     neck
    0.65
    POSITIVE LOGITS
    stitute
    0.75
    峋
    0.75
    নীতির
    0.74
    roir
    0.72
    riwal
    0.70
    fty
    0.69
    ifred
    0.69
    장이
    0.69
    ỹ
    0.68
    フィル
    0.68
    Act Density 0.002%

    No Known Activations