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

    Neuronpedia

    INDEX
    Explanations

    Nielsen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adverse
    -0.06
     الی
    -0.06
     timber
    -0.06
     halfway
    -0.06
     gently
    -0.06
    Pr
    -0.06
     hasta
    -0.06
    neği
    -0.06
     Bour
    -0.06
    .fix
    -0.05
    POSITIVE LOGITS
    λλην
    0.08
    컴
    0.08
    추
    0.08
    MQ
    0.07
     AppMethodBeat
    0.07
     enim
    0.07
     IBM
    0.07
     одном
    0.07
     Automatic
    0.07
     Birmingham
    0.07
    Act Density 0.001%

    No Known Activations