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

    Neuronpedia

    INDEX
    Explanations

    technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anymore
    -0.08
    "+"
    -0.07
     Convers
    -0.07
    First
    -0.06
     momentum
    -0.06
     supervised
    -0.06
    ame
    -0.06
    .easing
    -0.06
     outlined
    -0.06
    َد
    -0.06
    POSITIVE LOGITS
     quelque
    0.08
     kako
    0.07
    elerinin
    0.07
     Playstation
    0.06
     doprav
    0.06
     прос
    0.06
    wx
    0.06
     trouvé
    0.06
     quận
    0.06
    (mutex
    0.06
    Act Density 0.003%

    No Known Activations