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

    Neuronpedia

    INDEX
    Explanations

    role playing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rej
    -0.07
     ldb
    -0.06
    يج
    -0.06
    พล
    -0.06
     Baz
    -0.06
    ήλ
    -0.06
     UIScreen
    -0.06
    layan
    -0.06
     blush
    -0.06
     acet
    -0.06
    POSITIVE LOGITS
    _SAMPLES
    0.06
    _MODE
    0.06
     chú
    0.06
    ayız
    0.06
    midd
    0.06
    lymp
    0.06
    ')));↵
    0.06
     prompted
    0.06
     disadvantage
    0.06
     probability
    0.06
    Act Density 0.016%

    No Known Activations