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
     Wiring
    -0.07
    ESSAGE
    -0.07
    geber
    -0.07
    errer
    -0.06
    .showToast
    -0.06
    청
    -0.06
    /print
    -0.06
    aro
    -0.06
    elloworld
    -0.06
     ayında
    -0.06
    POSITIVE LOGITS
     простран
    0.06
     wars
    0.06
    	queue
    0.06
    )<
    0.06
    ↵			↵
    0.06
     gravitational
    0.06
     		↵
    0.06
     karşısında
    0.05
     bibli
    0.05
    ,"
    0.05
    Act Density 0.025%

    No Known Activations