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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    msp
    -0.08
     Αθή
    -0.07
    едагог
    -0.06
     دهد
    -0.06
    างว
    -0.06
     Duo
    -0.06
     Jacques
    -0.06
    给我
    -0.06
     pew
    -0.06
    uin
    -0.06
    POSITIVE LOGITS
     longing
    0.06
    _beh
    0.06
    routes
    0.06
    unity
    0.06
    tiles
    0.06
    .head
    0.06
    _graph
    0.06
     Beh
    0.06
    locking
    0.06
     UIImage
    0.06
    Act Density 0.103%

    No Known Activations