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

    Neuronpedia

    INDEX
    Explanations

    endoth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repetition
    -0.06
     tutto
    -0.06
    wij
    -0.06
     FI
    -0.06
    -my
    -0.06
     deren
    -0.06
    EN
    -0.06
    ,text
    -0.06
     kitten
    -0.05
    lemetry
    -0.05
    POSITIVE LOGITS
     endoth
    0.10
    should
    0.07
    inheritdoc
    0.07
     smugg
    0.07
    adığ
    0.07
     seamlessly
    0.07
    off
    0.07
    /Sub
    0.06
     Venom
    0.06
    ydro
    0.06
    Act Density 0.004%

    No Known Activations