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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _price
    -0.07
    .cart
    -0.07
    _state
    -0.07
    _dictionary
    -0.06
     kalk
    -0.06
     Name
    -0.06
    profile
    -0.06
    sz
    -0.06
    embers
    -0.06
    verbosity
    -0.06
    POSITIVE LOGITS
     Beacon
    0.07
    jejer
    0.07
    	bt
    0.07
     полот
    0.07
     Spears
    0.06
    Gün
    0.06
     Mayo
    0.06
    Odd
    0.06
     synthetic
    0.06
     �
    0.06
    Act Density 0.064%

    No Known Activations