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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /ac
    -0.07
     pads
    -0.06
     ambiance
    -0.06
    	long
    -0.06
    aug
    -0.06
     distress
    -0.06
    αι
    -0.06
    仪
    -0.06
    âl
    -0.06
    िब
    -0.06
    POSITIVE LOGITS
    ález
    0.07
     anthropology
    0.07
     největší
    0.07
    .ReLU
    0.06
    ।↵
    0.06
     feu
    0.06
    γγραφ
    0.06
     )[
    0.06
    semicolon
    0.06
    .examples
    0.06
    Act Density 0.016%

    No Known Activations