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

    Neuronpedia

    INDEX
    Explanations

    chemical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ambassador
    -0.07
     ambassador
    -0.06
     {{↵
    -0.06
    -directory
    -0.06
    (Device
    -0.06
    Ban
    -0.06
    าคา
    -0.06
    _PROGRAM
    -0.06
    _CHARSET
    -0.06
    grams
    -0.06
    POSITIVE LOGITS
     FAILURE
    0.06
     prevented
    0.06
     waited
    0.06
    _down
    0.06
    _undo
    0.06
    аток
    0.05
     tcp
    0.05
     scale
    0.05
     modified
    0.05
    атов
    0.05
    Act Density 0.023%

    No Known Activations