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

    Neuronpedia

    INDEX
    Explanations

    code or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    『
    0.41
    MH
    0.39
     artisan
    0.39
     formerly
    0.37
     puse
    0.36
    Directory
    0.36
     『
    0.36
    inesis
    0.36
     entertainers
    0.36
    formerly
    0.35
    POSITIVE LOGITS
    েক
    0.45
     jaanu
    0.44
     kepada
    0.40
     सदन
    0.40
    ruitment
    0.39
    їн
    0.38
     видом
    0.38
     vuelva
    0.38
     Bewer
    0.38
     dhammo
    0.38
    Act Density 0.000%

    No Known Activations