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

    Neuronpedia

    INDEX
    Explanations

    alphabetical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elt
    -0.06
    .aw
    -0.06
    667
    -0.06
     глуб
    -0.06
    _cmd
    -0.06
    -energy
    -0.06
    .guna
    -0.06
    debug
    -0.06
     Ammo
    -0.06
    _icons
    -0.05
    POSITIVE LOGITS
     listed
    0.07
    няття
    0.07
    품
    0.07
     cấp
    0.07
     personalized
    0.07
    ection
    0.07
    ITOR
    0.07
     redirected
    0.07
    kan
    0.07
     personalize
    0.07
    Act Density 0.003%

    No Known Activations