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

    Neuronpedia

    INDEX
    Explanations

    redistributed

    np_max-act · gemini-2.0-flash

    words related to crime or accusations of wrongdoing.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     обыч
    -0.06
     userManager
    -0.06
    емати
    -0.06
    روس
    -0.06
    zen
    -0.06
    _UTILS
    -0.06
    ispens
    -0.06
     english
    -0.06
    .Orientation
    -0.06
     mListener
    -0.06
    POSITIVE LOGITS
     redistributed
    0.07
    _SID
    0.06
     quil
    0.06
    ��
    0.06
    >)↵
    0.06
    -da
    0.06
    alted
    0.06
     Cộng
    0.05
    ΑΤ
    0.05
    OPER
    0.05
    Act Density 0.001%

    No Known Activations