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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wag
    -0.07
    .ba
    -0.07
     материал
    -0.07
    ιακ
    -0.07
    ’à
    -0.06
    ㆍ
    -0.06
     �
    -0.06
     belli
    -0.06
    oubted
    -0.06
     beurette
    -0.06
    POSITIVE LOGITS
     maturity
    0.07
     velocity
    0.07
     manners
    0.07
     velocities
    0.07
     taste
    0.07
     basin
    0.07
     ngoại
    0.07
     Updating
    0.07
     Kind
    0.06
    ěji
    0.06
    Act Density 0.000%

    No Known Activations