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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ひと
    -0.07
     Sector
    -0.07
     tends
    -0.07
    有必要
    -0.07
    TextStyle
    -0.07
    Suite
    -0.07
    真切
    -0.07
    わけ
    -0.06
    ほ
    -0.06
    淹没
    -0.06
    POSITIVE LOGITS
     omas
    0.07
     Playing
    0.07
    former
    0.07
    -reg
    0.07
     principles
    0.07
    <Car
    0.07
    _relations
    0.06
     Ła
    0.06
    Formation
    0.06
     Imp
    0.06
    Act Density 0.010%

    No Known Activations