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

    Neuronpedia

    INDEX
    Explanations

    sci

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     land
    -0.07
    _membership
    -0.06
     Chair
    -0.06
     Fro
    -0.06
     BLOCK
    -0.06
     meny
    -0.06
     wells
    -0.06
     Пот
    -0.06
     Fres
    -0.06
    Amb
    -0.06
    POSITIVE LOGITS
    ワ
    0.07
    irler
    0.06
    0.06
    obbies
    0.06
    errer
    0.06
    чив
    0.06
    ň
    0.06
    =get
    0.06
    贸
    0.06
    άζ
    0.06
    Act Density 0.002%

    No Known Activations