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

    Neuronpedia

    INDEX
    Explanations

    dialogues and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    　ヽ
    -0.07
     Ή
    -0.07
     CRS
    -0.07
     arena
    -0.07
     yerini
    -0.06
     capitalized
    -0.06
     trout
    -0.06
     hands
    -0.06
     intervened
    -0.06
     Fans
    -0.06
    POSITIVE LOGITS
     Relay
    0.06
     ویژگی
    0.06
    ,double
    0.06
     malaysia
    0.06
     Vietnamese
    0.06
     uží
    0.06
    arseille
    0.06
    .edu
    0.06
     vin
    0.06
    TIME
    0.06
    Act Density 0.042%

    No Known Activations