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

    Neuronpedia

    INDEX
    Explanations

    floating-point numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نم
    -0.07
     Spiel
    -0.07
     či
    -0.06
    (spell
    -0.06
    luk
    -0.06
     sentimental
    -0.06
    _Null
    -0.06
     przypad
    -0.06
    bedo
    -0.06
    meer
    -0.06
    POSITIVE LOGITS
    Particles
    0.07
     constructed
    0.07
    Core
    0.07
     capped
    0.06
     />\
    0.06
    Soon
    0.06
     사실
    0.06
    Cmd
    0.06
     son
    0.06
    Regions
    0.06
    Act Density 0.011%

    No Known Activations