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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NG
    -0.07
     nause
    -0.07
     Null
    -0.06
     complexities
    -0.06
     delt
    -0.06
    =(-
    -0.06
     سخ
    -0.06
    SN
    -0.06
     реак
    -0.06
    /oauth
    -0.06
    POSITIVE LOGITS
    	dto
    0.07
     Escort
    0.06
    }"↵
    0.06
    ']);↵↵
    0.06
    ])↵
    0.06
     Formatter
    0.06
     Einsatz
    0.06
    athon
    0.06
    )"↵
    0.06
    ClassName
    0.06
    Act Density 0.000%

    No Known Activations