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

    Neuronpedia

    INDEX
    Explanations

    liability disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STE
    -0.07
     Ere
    -0.07
    ием
    -0.07
    ele
    -0.07
    ору
    -0.07
    .Lines
    -0.07
    pper
    -0.07
    andre
    -0.06
    illo
    -0.06
    oun
    -0.06
    POSITIVE LOGITS
     startActivity
    0.07
    BufferSize
    0.07
     shocked
    0.06
     Kidd
    0.06
    ZZ
    0.06
     bewild
    0.06
    稱
    0.06
     holidays
    0.06
     pornôs
    0.06
     pleased
    0.06
    Act Density 0.000%

    No Known Activations