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
    	loop
    -0.07
     رأ
    -0.07
     urgent
    -0.07
     userDetails
    -0.06
     instantly
    -0.06
    ?}",
    -0.06
     congressman
    -0.06
    :update
    -0.06
    -rise
    -0.06
     words
    -0.06
    POSITIVE LOGITS
     Pam
    0.07
     Zig
    0.07
    DJ
    0.07
    578
    0.06
     dog
    0.06
    codile
    0.06
    leveland
    0.06
     Tot
    0.06
     источ
    0.06
    ilon
    0.06
    Act Density 0.000%

    No Known Activations