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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dresses
    -0.07
     přímo
    -0.07
     fucks
    -0.06
     wil
    -0.06
     ia
    -0.06
     đôi
    -0.06
     urine
    -0.06
     handles
    -0.06
     참여
    -0.06
    ёл
    -0.06
    POSITIVE LOGITS
    _EXIT
    0.07
    weet
    0.07
    }}},↵
    0.07
    ondon
    0.07
    -fed
    0.06
    -x
    0.06
    -\
    0.06
    ovable
    0.06
     %-
    0.06
    -stop
    0.06
    Act Density 0.065%

    No Known Activations