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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ляем
    -0.07
    ivot
    -0.06
     Liam
    -0.06
    _fid
    -0.06
    (search
    -0.06
     اقتص
    -0.06
    benchmark
    -0.06
    (PARAM
    -0.06
    _EN
    -0.06
     obt
    -0.06
    POSITIVE LOGITS
    _MAKE
    0.07
    انيا
    0.07
    訓
    0.07
     unfairly
    0.06
    озв
    0.06
    社会
    0.06
     Eleanor
    0.06
     alm
    0.06
     Rosie
    0.06
    ENTS
    0.06
    Act Density 0.018%

    No Known Activations