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

    Neuronpedia

    INDEX
    Explanations

    knees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coming
    -0.06
    �
    -0.06
     Obamacare
    -0.06
    Cd
    -0.06
     |=
    -0.06
     الو
    -0.06
    (att
    -0.06
     nep
    -0.06
    lection
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     troops
    0.07
    Detect
    0.07
     resourceName
    0.07
    robe
    0.06
     mental
    0.06
    bakan
    0.06
    tfoot
    0.06
    Animal
    0.06
    move
    0.06
    ousel
    0.06
    Act Density 0.006%

    No Known Activations