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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intimidating
    -0.07
     memorandum
    -0.06
     nuestro
    -0.06
     Apartment
    -0.06
    enos
    -0.06
     remed
    -0.06
    แล
    -0.06
     twisting
    -0.06
    verification
    -0.06
     막
    -0.06
    POSITIVE LOGITS
    _bio
    0.06
    asted
    0.06
    map
    0.06
    (vc
    0.06
    (GameObject
    0.06
     "|"
    0.06
    *(-
    0.06
     série
    0.06
    Ậ
    0.06
     न
    0.06
    Act Density 0.005%

    No Known Activations