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

    Neuronpedia

    INDEX
    Explanations

    say prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Think
    -0.07
     Mueller
    -0.06
    ⁎
    -0.06
    辦理
    -0.06
    一樣
    -0.06
     Muslim
    -0.06
    通往
    -0.06
     conform
    -0.06
    ––
    -0.06
    rü
    -0.06
    POSITIVE LOGITS
    actoring
    0.07
     basePath
    0.07
    érc
    0.07
    ائق
    0.07
    avin
    0.06
    сор
    0.06
    _DSP
    0.06
    favorite
    0.06
    base
    0.06
     Об
    0.06
    Act Density 0.009%

    No Known Activations