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

    Neuronpedia

    INDEX
    Explanations

    Search

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    घ
    -0.06
    िप
    -0.06
    miss
    -0.06
    ेन
    -0.06
    DEST
    -0.06
     sacrifices
    -0.06
     连
    -0.06
    连
    -0.06
    違
    -0.06
     xy
    -0.05
    POSITIVE LOGITS
    (dot
    0.08
     участь
    0.07
    ota
    0.07
    vironments
    0.07
    .SizeType
    0.07
    .Asset
    0.06
    _ble
    0.06
     educate
    0.06
     типа
    0.06
    号
    0.06
    Act Density 0.000%

    No Known Activations