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

    Neuronpedia

    INDEX
    Explanations

    The followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alignat
    1.66
    烃
    1.60
    வட
    1.51
    தின
    1.49
     외국
    1.35
     கேள்வி
    1.35
     모두
    1.34
    XK
    1.32
     해외
    1.31
     diethyl
    1.31
    POSITIVE LOGITS
    ocrite
    1.77
    ixir
    1.75
    odore
    1.64
    odora
    1.63
    atre
    1.61
    atres
    1.56
    रस
    1.50
    likle
    1.48
    couple
    1.48
     stade
    1.47
    Act Density 0.257%

    No Known Activations