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

    Neuronpedia

    INDEX
    Explanations

    adequate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hiszen
    0.66
     appunto
    0.65
     embodiment
    0.65
    잖아요
    0.64
     terminology
    0.63
     manifestation
    0.63
     reflection
    0.62
    针对
    0.62
    manifest
    0.62
     insures
    0.61
    POSITIVE LOGITS
     decent
    2.06
     passable
    1.93
     mediocre
    1.82
     okay
    1.82
     непло
    1.81
     decently
    1.81
     respectable
    1.75
    okay
    1.59
     tolerable
    1.59
     acceptable
    1.58
    Act Density 0.614%

    No Known Activations