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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /res
    -0.07
    四十
    -0.07
     OnTriggerEnter
    -0.07
    潆
    -0.07
     самого
    -0.07
     north
    -0.07
    _BLEND
    -0.07
    毋
    -0.06
     NSMutable
    -0.06
    ModelProperty
    -0.06
    POSITIVE LOGITS
    rase
    0.07
     justification
    0.06
     aussi
    0.06
    ср
    0.06
     eats
    0.06
     McCain
    0.06
    Rate
    0.06
    strategy
    0.06
     bakeca
    0.06
    Å
    0.06
    Act Density 0.005%

    No Known Activations