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

    Neuronpedia

    INDEX
    Explanations

    procedural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    807
    -0.07
     zusammen
    -0.06
     needs
    -0.06
     drinkers
    -0.06
    oods
    -0.06
    IBLE
    -0.06
     Representative
    -0.06
    heits
    -0.06
    analy
    -0.06
    OST
    -0.06
    POSITIVE LOGITS
     procedural
    0.07
    /Footer
    0.07
    _RECE
    0.06
     Parse
    0.06
     Scalars
    0.06
     shutting
    0.06
    状況
    0.06
    ViewSet
    0.06
     облас
    0.06
    .CREATE
    0.06
    Act Density 0.002%

    No Known Activations