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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    价
    -0.07
     VERSION
    -0.07
     produtos
    -0.07
     Arabic
    -0.06
     PLAN
    -0.06
    ulo
    -0.06
     dynasty
    -0.06
     Fountain
    -0.06
    _DIR
    -0.06
     LINK
    -0.06
    POSITIVE LOGITS
     ",
↵
    0.07
    :pk
    0.07
    ([\
    0.06
    0.06
    なん
    0.06
    rvé
    0.06
     ensl
    0.06
    _AUX
    0.06
    /native
    0.06
     abused
    0.06
    Act Density 0.011%

    No Known Activations