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

    Neuronpedia

    INDEX
    Explanations

    norm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IGHL
    -0.06
    binations
    -0.06
     NVIC
    -0.06
    辞
    -0.06
    昭和
    -0.06
     termination
    -0.06
     місці
    -0.06
     квітня
    -0.06
     subordinate
    -0.06
     clever
    -0.06
    POSITIVE LOGITS
     norm
    0.27
     Norm
    0.14
    norm
    0.13
    Norm
    0.11
     norms
    0.10
    orm
    0.08
    _norm
    0.07
     Thông
    0.07
    .norm
    0.07
    (norm
    0.07
    Act Density 0.005%

    No Known Activations