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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,X
    -0.06
    Ζ
    -0.06
     Floors
    -0.06
    ft
    -0.06
    	D
    -0.06
     CWE
    -0.06
    Cl
    -0.06
     δι
    -0.06
     Augustine
    -0.06
    ظة
    -0.05
    POSITIVE LOGITS
     cook
    0.07
    (series
    0.06
    焦
    0.06
    íf
    0.06
    .me
    0.06
    ."'";↵
    0.06
     endorsing
    0.06
    .co
    0.06
     Fuji
    0.06
    /graph
    0.06
    Act Density 0.247%

    No Known Activations