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

    Neuronpedia

    INDEX
    Explanations

    logic and reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Demp
    -0.07
    ystate
    -0.06
    とか
    -0.06
    CG
    -0.06
    _iv
    -0.06
    .''↵↵
    -0.06
    ??↵↵
    -0.06
     Gall
    -0.06
     empres
    -0.06
     SEAL
    -0.06
    POSITIVE LOGITS
     anno
    0.07
    Illuminate
    0.07
    019
    0.06
    änger
    0.06
     channel
    0.06
    giene
    0.06
     �
    0.06
    annon
    0.06
     Sinatra
    0.06
    _FILE
    0.06
    Act Density 0.008%

    No Known Activations