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

    Neuronpedia

    INDEX
    Explanations

    programming and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     factories
    -0.07
     abb
    -0.07
     sprint
    -0.07
    めた
    -0.06
     Ed
    -0.06
     formidable
    -0.06
    聞
    -0.06
    estival
    -0.06
    ileo
    -0.06
     Rwanda
    -0.06
    POSITIVE LOGITS
    Hover
    0.07
    always
    0.06
     Sens
    0.06
     erklä
    0.06
     arrog
    0.06
    argout
    0.06
     Struct
    0.06
     　　 　
    0.06
     　　　　　
    0.06
     userName
    0.06
    Act Density 0.000%

    No Known Activations