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

    Neuronpedia

    INDEX
    Explanations

    Non-English characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loving
    -0.07
    貨
    -0.07
     anticipated
    -0.07
    arians
    -0.06
    travel
    -0.06
     вра
    -0.06
     fault
    -0.06
    605
    -0.06
    Division
    -0.06
    (un
    -0.06
    POSITIVE LOGITS
     фев
    0.06
     предназнач
    0.06
    γρα
    0.06
     Jenner
    0.06
    	opts
    0.06
    ğ
    0.06
    漂
    0.06
     Humph
    0.06
     Při
    0.06
     \%
    0.06
    Act Density 0.107%

    No Known Activations