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

    Neuronpedia

    INDEX
    Explanations

    whatever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TOCOL
    -0.07
    (金
    -0.07
     tableau
    -0.06
    ользов
    -0.06
     exemplary
    -0.06
     money
    -0.06
     currency
    -0.06
     sociale
    -0.06
     протягом
    -0.06
    ление
    -0.06
    POSITIVE LOGITS
    _MT
    0.07
    "=>$
    0.07
    異
    0.07
    039
    0.06
    ='".
    0.06
    dent
    0.06
     мот
    0.06
     +#+#+#+
    0.06
     quartz
    0.06
    株
    0.06
    Act Density 0.023%

    No Known Activations