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

    Neuronpedia

    INDEX
    Explanations

    opinion articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToRemove
    -0.07
    dorf
    -0.07
     Scenes
    -0.07
    Locations
    -0.06
    ᐖ
    -0.06
    .UltraWin
    -0.06
    cales
    -0.06
    /select
    -0.06
    �
    -0.06
     doctr
    -0.06
    POSITIVE LOGITS
    擁
    0.08
    Most
    0.07
    creation
    0.07
    .lambda
    0.06
     README
    0.06
    -K
    0.06
    永久
    0.06
    .randomUUID
    0.06
    .json
    0.06
    搭配
    0.06
    Act Density 0.154%

    No Known Activations