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

    Neuronpedia

    INDEX
    Explanations

    useful text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dai
    -0.07
     púb
    -0.07
     Liz
    -0.06
     focus
    -0.06
     Dia
    -0.06
    공지
    -0.06
    _PA
    -0.06
    coeff
    -0.06
    Ngoài
    -0.06
     fizz
    -0.06
    POSITIVE LOGITS
     �
    0.07
     rape
    0.06
     Geometry
    0.06
     Jewish
    0.06
     zav
    0.06
     TO
    0.06
    Additionally
    0.06
     tavern
    0.06
     MPU
    0.06
    _rent
    0.06
    Act Density 0.000%

    No Known Activations