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

    Neuronpedia

    INDEX
    Explanations

    option

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stadt
    -0.07
    decrypt
    -0.07
    _organization
    -0.07
     decay
    -0.07
    찌
    -0.06
    »↵↵
    -0.06
     chief
    -0.06
    _regs
    -0.06
    ischen
    -0.06
     Cher
    -0.06
    POSITIVE LOGITS
    γγ
    0.07
    )/(
    0.07
    牙
    0.06
     sued
    0.06
    lated
    0.06
    .air
    0.06
    .ss
    0.06
    тиров
    0.06
    тех
    0.06
    ))/(
    0.06
    Act Density 0.006%

    No Known Activations