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

    Neuronpedia

    INDEX
    Explanations

    Beginning of sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     incid
    -0.07
    ,…↵↵
    -0.07
    Dropdown
    -0.06
    fout
    -0.06
    oot
    -0.06
     ignited
    -0.06
     interf
    -0.06
    PD
    -0.06
     folding
    -0.06
    POSITIVE LOGITS
     pacman
    0.07
    StepThrough
    0.06
     فيه
    0.06
    .transactions
    0.06
    _SYSTEM
    0.06
    .Automation
    0.06
    (Target
    0.06
    ="../../
    0.06
    (fixture
    0.06
     eager
    0.06
    Act Density 0.131%

    No Known Activations