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

    Neuronpedia

    INDEX
    Explanations

    prepositions and articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Factor
    -0.08
    _disp
    -0.07
     Bond
    -0.07
    loo
    -0.07
    shaft
    -0.07
    (encoding
    -0.06
    ρο
    -0.06
    Female
    -0.06
    Mag
    -0.06
    otropic
    -0.06
    POSITIVE LOGITS
     MAIN
    0.07
     yeniden
    0.06
     थ
    0.06
    ập
    0.06
     empres
    0.06
     Česká
    0.06
     Informationen
    0.06
     след
    0.06
    PROGRAM
    0.06
     faiz
    0.06
    Act Density 0.010%

    No Known Activations