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

    Neuronpedia

    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hoog
    -0.07
     cuc
    -0.07
     Ginger
    -0.07
    ACHINE
    -0.07
    7
    -0.06
     Cater
    -0.06
     artic
    -0.06
    webs
    -0.06
     prestige
    -0.06
     produto
    -0.06
    POSITIVE LOGITS
    Always
    0.07
     newState
    0.07
     اج
    0.06
    (GLFW
    0.06
     StObject
    0.06
    ="";
↵
    0.06
    리스
    0.06
    Throughout
    0.06
     майбут
    0.06
     Bowie
    0.06
    Act Density 0.046%

    No Known Activations