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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _seg
    -0.07
     ciclo
    -0.07
     Mentor
    -0.06
     Friends
    -0.06
     Toy
    -0.06
     Echo
    -0.06
    -changing
    -0.06
     getOrder
    -0.06
     swagger
    -0.06
     fears
    -0.06
    POSITIVE LOGITS
     vale
    0.07
    ===========
    0.06
     denne
    0.06
    われる
    0.06
    arms
    0.06
    ustralian
    0.06
    onymous
    0.06
     obsess
    0.06
    ≦
    0.06
    ีส
    0.06
    Act Density 0.012%

    No Known Activations