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

    Neuronpedia

    INDEX
    Explanations

    programming and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    would
    -0.07
    berger
    -0.07
     Мас
    -0.07
     Bh
    -0.07
     Courts
    -0.07
    ificado
    -0.06
     Iss
    -0.06
     Balk
    -0.06
    -bel
    -0.06
    -social
    -0.06
    POSITIVE LOGITS
     tbody
    0.07
    .gpu
    0.06
    /em
    0.06
    .datetime
    0.06
     effective
    0.06
    	admin
    0.06
     onKeyDown
    0.06
     форми
    0.06
     streamline
    0.06
     textField
    0.06
    Act Density 0.000%

    No Known Activations