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

    Neuronpedia

    INDEX
    Explanations

    Road locations and directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rm
    -0.07
    (map
    -0.06
     rg
    -0.06
    üslüman
    -0.06
     models
    -0.06
     inserted
    -0.06
     flowers
    -0.06
    альна
    -0.06
    datetime
    -0.06
     Collections
    -0.06
    POSITIVE LOGITS
    บาย
    0.07
     misdemeanor
    0.07
     ابو
    0.06
    _SENS
    0.06
    _NPC
    0.06
     launder
    0.06
     misdemean
    0.06
    EMON
    0.06
     abre
    0.06
    ुआ
    0.06
    Act Density 0.003%

    No Known Activations