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

    Neuronpedia

    INDEX
    Explanations

    backticks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -loading
    -0.08
     YM
    -0.07
    是不可能
    -0.07
     UnsupportedOperationException
    -0.07
    _ASC
    -0.07
     Opera
    -0.07
    ishlist
    -0.07
     errMsg
    -0.07
    umbnail
    -0.07
     blanks
    -0.07
    POSITIVE LOGITS
    摧毁
    0.08
    '))↵
    0.07
    Pri
    0.07
    states
    0.07
     Cult
    0.07
    굄
    0.07
     вод
    0.07
     intervened
    0.07
    eu
    0.07
    ват
    0.07
    Act Density 0.022%

    No Known Activations