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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    モ
    -0.08
    Tahoma
    -0.07
    xDF
    -0.06
    laps
    -0.06
    stim
    -0.06
     befind
    -0.06
     Wis
    -0.06
     متف
    -0.06
    ीटर
    -0.06
    ottesville
    -0.06
    POSITIVE LOGITS
     Subcommittee
    0.07
    0.07
     promises
    0.07
    -large
    0.07
     beverages
    0.06
    ा.↵
    0.06
    ORDER
    0.06
     regularization
    0.06
     --------↵
    0.06
     several
    0.06
    Act Density 0.003%

    No Known Activations