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

    Neuronpedia

    INDEX
    Explanations

    Code and Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recorder
    -0.08
     dissolve
    -0.07
    Reporter
    -0.07
     gym
    -0.07
     Chamber
    -0.06
    /maps
    -0.06
    vy
    -0.06
     Phaser
    -0.06
     sayısı
    -0.06
     series
    -0.06
    POSITIVE LOGITS
    ::~
    0.07
    ご�
    0.07
     conditional
    0.07
     dernier
    0.07
    (Client
    0.07
    .front
    0.07
    (Output
    0.07
     Lesson
    0.07
    solution
    0.07
     différence
    0.06
    Act Density 0.038%

    No Known Activations