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

    Neuronpedia

    INDEX
    Explanations

    each and has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    diet
    -0.09
     بازی
    -0.08
    PLAY
    -0.08
    irth
    -0.07
    cep
    -0.07
    gült
    -0.07
    Chosen
    -0.07
     کھیل
    -0.07
     unusually
    -0.07
    versorgung
    -0.07
    POSITIVE LOGITS
     contributes
    0.10
    마다
    0.09
     kontrib
    0.09
     contribute
    0.08
     sebanyak
    0.08
     योगदान
    0.08
     counted
    0.08
     gemiddeld
    0.08
     ensin
    0.07
    Mur
    0.07
    Act Density 0.035%

    No Known Activations