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

    Neuronpedia

    INDEX
    Explanations

    Code/Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .only
    -0.07
     données
    -0.06
     feasible
    -0.06
    	version
    -0.06
     ape
    -0.06
     thầu
    -0.06
     nao
    -0.06
    恵
    -0.06
    羽
    -0.06
    ::~
    -0.06
    POSITIVE LOGITS
    /Web
    0.07
    von
    0.07
    /img
    0.07
     finals
    0.07
    ./(
    0.06
     tails
    0.06
     lign
    0.06
    Constructor
    0.06
     Did
    0.06
     steel
    0.06
    Act Density 0.000%

    No Known Activations