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

    Neuronpedia

    INDEX
    Explanations

    intervention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     див
    -0.07
     Cob
    -0.07
    jsonData
    -0.07
    (bb
    -0.06
     Fragen
    -0.06
    ’B
    -0.06
     арми
    -0.06
     件
    -0.06
    ρκε
    -0.06
    Remark
    -0.06
    POSITIVE LOGITS
    326
    0.07
    Xi
    0.07
    330
    0.06
    	click
    0.06
     lcm
    0.06
     arac
    0.06
    #include
    0.06
    廊
    0.06
     péri
    0.06
    iatric
    0.06
    Act Density 0.150%

    No Known Activations