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

    Neuronpedia

    INDEX
    Explanations

    Giving permission/invitation in conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _hashes
    -0.07
     Significant
    -0.06
    pcf
    -0.06
    ological
    -0.06
    -spinner
    -0.06
    Pieces
    -0.06
    ト
    -0.06
     }))↵
    -0.06
     trăm
    -0.06
     irreversible
    -0.06
    POSITIVE LOGITS
    uthor
    0.07
    ighter
    0.07
    .food
    0.07
    (mat
    0.06
     fighter
    0.06
    .sql
    0.06
     logged
    0.06
     ＿
    0.06
     dispon
    0.06
    	LOGGER
    0.06
    Act Density 0.182%

    No Known Activations