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

    Neuronpedia

    INDEX
    Explanations

    mg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ircles
    -0.06
    _logo
    -0.06
     stopwords
    -0.06
    378
    -0.06
     station
    -0.06
     선
    -0.06
     организ
    -0.06
     segunda
    -0.06
     sys
    -0.06
    ={$
    -0.06
    POSITIVE LOGITS
    avax
    0.07
    黒
    0.06
     Orientation
    0.06
    umbling
    0.06
     HelloWorld
    0.06
    .Long
    0.06
    Lens
    0.06
    orientation
    0.06
     Matth
    0.06
    fell
    0.05
    Act Density 0.000%

    No Known Activations