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

    Neuronpedia

    INDEX
    Explanations

    GUI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deterministic
    -0.07
    768
    -0.07
     boiler
    -0.06
    -body
    -0.06
    кадем
    -0.06
    );


↵
    -0.06
     Surely
    -0.06
    _apply
    -0.06
     Fuller
    -0.06
     Hollywood
    -0.06
    POSITIVE LOGITS
    -interface
    0.06
    _CHAR
    0.06
    medi
    0.06
    (ui
    0.06
     любой
    0.06
    lector
    0.06
     inflict
    0.06
    Demon
    0.06
    EXPECT
    0.06
    levation
    0.06
    Act Density 0.012%

    No Known Activations