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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    George
    -0.07
     Sun
    -0.07
    House
    -0.07
     През
    -0.06
    最近
    -0.06
    Estado
    -0.06
    Ca
    -0.06
     George
    -0.06
    _appro
    -0.06
    pragma
    -0.06
    POSITIVE LOGITS
    ฯ
    0.07
    öt
    0.06
    ên
    0.06
    .nlm
    0.06
    .helper
    0.06
    äge
    0.06
    _camera
    0.06
    �
    0.06
    libc
    0.06
    ttl
    0.06
    Act Density 0.004%

    No Known Activations