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

    Neuronpedia

    INDEX
    Explanations

    benches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uzu
    -0.07
    ('=
    -0.06
    CppGeneric
    -0.06
     celebrity
    -0.06
    ilk
    -0.06
     реп
    -0.06
     Garlic
    -0.06
     Sak
    -0.06
    анием
    -0.06
    ار
    -0.06
    POSITIVE LOGITS
    _od
    0.07
    ver
    0.06
     injuries
    0.06
     engine
    0.06
    Sch
    0.06
     Universal
    0.06
    bs
    0.06
    oge
    0.06
    stra
    0.06
    PET
    0.06
    Act Density 0.000%

    No Known Activations