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

    Neuronpedia

    INDEX
    Explanations

    `

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     personality
    -0.07
    plementation
    -0.07
     disadvantage
    -0.07
     Beaver
    -0.07
    AppBar
    -0.06
     Clover
    -0.06
     disaster
    -0.06
    _BUFF
    -0.06
     Personality
    -0.06
    append
    -0.06
    POSITIVE LOGITS
    udit
    0.07
     防
    0.07
    acyj
    0.06
     eget
    0.06
     nejd
    0.06
     vítěz
    0.06
     waitress
    0.06
    리의
    0.06
     />}↵
    0.06
     MQ
    0.06
    Act Density 0.003%

    No Known Activations