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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hunts
    -0.07
     Directors
    -0.07
    지역
    -0.07
     Muslims
    -0.07
     κοι
    -0.07
     mans
    -0.06
     unchanged
    -0.06
     Benefit
    -0.06
    _digits
    -0.06
    /umd
    -0.06
    POSITIVE LOGITS
    514
    0.07
    ROLE
    0.07
    UES
    0.06
    RING
    0.06
    	core
    0.06
     PPP
    0.06
    cházet
    0.06
    SIM
    0.06
    enght
    0.06
     GLFW
    0.06
    Act Density 0.000%

    No Known Activations