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

    Neuronpedia

    INDEX
    Explanations

    Explanations or instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    select
    -0.06
     Nx
    -0.06
    да
    -0.06
    (actor
    -0.06
     develop
    -0.06
     hypert
    -0.06
    billing
    -0.06
    .Add
    -0.06
    ело
    -0.06
    446
    -0.06
    POSITIVE LOGITS
     THANK
    0.07
    記事
    0.06
    .truth
    0.06
    ++)
↵
    0.06
     nye
    0.06
    _LABEL
    0.06
     Ctrl
    0.06
    (describing
    0.06
    FINITY
    0.06
    .sendRedirect
    0.06
    Act Density 0.159%

    No Known Activations