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

    Neuronpedia

    INDEX
    Explanations

    Role-playing/Storytelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    from
    -0.07
     características
    -0.07
     %[
    -0.07
     паль
    -0.07
     symbols
    -0.07
    prior
    -0.06
     optionally
    -0.06
    tests
    -0.06
    normal
    -0.06
    circle
    -0.06
    POSITIVE LOGITS
     UV
    0.06
    /platform
    0.06
    UED
    0.06
     -:-
    0.06
    APPED
    0.06
     branded
    0.06
    ANCED
    0.06
    	mutex
    0.06
     infinity
    0.06
    >>&
    0.06
    Act Density 0.004%

    No Known Activations