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

    Neuronpedia

    INDEX
    Explanations

    chaos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vara
    -0.07
    τογραφ
    -0.07
    兩
    -0.06
     slender
    -0.06
     sly
    -0.06
     heterosexual
    -0.06
     firstname
    -0.06
     lodge
    -0.06
    newValue
    -0.06
     tady
    -0.06
    POSITIVE LOGITS
     chaos
    0.09
     chaotic
    0.08
     Chaos
    0.07
     CAN
    0.07
    _IC
    0.07
    _SA
    0.07
     nightmare
    0.06
     gas
    0.06
     Tur
    0.06
    _IOCTL
    0.06
    Act Density 0.016%

    No Known Activations