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

    Neuronpedia

    INDEX
    Explanations

    advice and suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dir
    -0.07
    _years
    -0.06
    blob
    -0.06
     playbook
    -0.06
    .files
    -0.06
    _files
    -0.06
    tb
    -0.06
    patch
    -0.06
     modeled
    -0.06
     tiger
    -0.06
    POSITIVE LOGITS
     이제
    0.07
     nějaké
    0.07
    requently
    0.07
     수
    0.07
     των
    0.07
     fate
    0.06
    ของ
    0.06
    /new
    0.06
    _super
    0.06
     prostřed
    0.06
    Act Density 0.053%

    No Known Activations