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

    Neuronpedia

    INDEX
    Explanations

    Data followed by types or contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    БО
    0.37
     Minnesota
    0.35
    ㅕ
    0.34
    研
    0.34
    輕
    0.34
    䔧
    0.34
     strange
    0.34
    lwjgl
    0.33
     Substance
    0.33
    ighth
    0.33
    POSITIVE LOGITS
    зона
    0.45
     deadlines
    0.39
     sharing
    0.39
    flow
    0.38
     drastic
    0.38
     plane
    0.38
     tre
    0.37
     manip
    0.37
    wheel
    0.37
     trans
    0.37
    Act Density 0.025%

    No Known Activations