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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     needles
    -0.08
     headlines
    -0.06
     Hermione
    -0.06
     بهره
    -0.06
     мас
    -0.06
    bac
    -0.06
     Zusammen
    -0.06
    _SENT
    -0.06
     deton
    -0.06
     UC
    -0.06
    POSITIVE LOGITS
    '][]
    0.07
    озвращ
    0.06
    销
    0.06
     REQ
    0.06
     자동
    0.06
    	Message
    0.06
    wx
    0.06
    	fd
    0.06
     interpreter
    0.06
     encuentra
    0.06
    Act Density 0.069%

    No Known Activations