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

    Neuronpedia

    INDEX
    Explanations

    and, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쓰
    -0.07
    ells
    -0.07
    たちは
    -0.07
    �
    -0.06
     اروپا
    -0.06
     СССР
    -0.06
    рит
    -0.06
    らの
    -0.06
    Blocks
    -0.06
    ACCEPT
    -0.06
    POSITIVE LOGITS
    _tele
    0.07
     ERR
    0.07
     talent
    0.07
     пи
    0.06
     İslam
    0.06
    Sphere
    0.06
     Cobb
    0.06
     Wooden
    0.06
     generate
    0.06
    Meanwhile
    0.06
    Act Density 0.017%

    No Known Activations