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

    Neuronpedia

    INDEX
    Explanations

    GNU

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    functions
    -0.08
    	game
    -0.07
     crianças
    -0.07
    taş
    -0.07
    .physics
    -0.07
     guardians
    -0.07
     האחרון
    -0.07
     southwestern
    -0.07
     companions
    -0.07
     Campos
    -0.07
    POSITIVE LOGITS
    _VER
    0.07
    原创
    0.07
    য
    0.07
     easy
    0.06
    izin
    0.06
     translating
    0.06
    应收账
    0.06
    —one
    0.06
     pObj
    0.06
    જ
    0.06
    Act Density 0.001%

    No Known Activations