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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lo
    -0.07
     }↵↵↵↵↵
    -0.07
     расп
    -0.07
    Our
    -0.06
    RF
    -0.06
     toString
    -0.06
    	socket
    -0.06
     grp
    -0.06
     Kick
    -0.06
    Generic
    -0.06
    POSITIVE LOGITS
    一緒
    0.07
     abuse
    0.07
    .address
    0.06
     yaşayan
    0.06
    (express
    0.06
     spyOn
    0.06
    [d
    0.06
    _firstname
    0.06
     instances
    0.06
    报名
    0.06
    Act Density 0.014%

    No Known Activations