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

    Neuronpedia

    INDEX
    Explanations

    become

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mã
    -0.07
     hh
    -0.07
    osity
    -0.06
     eSports
    -0.06
     tray
    -0.06
     أح
    -0.06
     �
    -0.06
     oppression
    -0.06
     IF
    -0.06
     dao
    -0.06
    POSITIVE LOGITS
     gravid
    0.06
    \system
    0.06
    Receipt
    0.06
    .calls
    0.06
     BadRequest
    0.06
    [position
    0.06
    fire
    0.06
    ToLeft
    0.06
    Overrides
    0.06
    　イ
    0.06
    Act Density 0.188%

    No Known Activations