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

    Neuronpedia

    INDEX
    Explanations

    sorted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cell
    -0.07
     Spiritual
    -0.07
    linky
    -0.06
    esto
    -0.06
     (){↵
    -0.06
    ”).
    -0.06
     computations
    -0.06
     paralysis
    -0.06
    .Sprite
    -0.06
     suggesting
    -0.06
    POSITIVE LOGITS
    だな
    0.07
    .annot
    0.06
    Holy
    0.06
    �다
    0.06
     lucrative
    0.06
    OOK
    0.06
    ặ
    0.06
    autoload
    0.06
    bral
    0.06
     определ
    0.06
    Act Density 0.005%

    No Known Activations