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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    probe
    -0.09
    oute
    -0.07
    watch
    -0.07
    comp
    -0.07
     National
    -0.06
     sourced
    -0.06
     Techniques
    -0.06
     dispute
    -0.06
    change
    -0.06
    .table
    -0.06
    POSITIVE LOGITS
    Duration
    0.07
     בתור
    0.07
    _GRA
    0.07
    EventManager
    0.07
     tarde
    0.07
    以後
    0.07
     Favorites
    0.07
    .createNew
    0.07
     مجر
    0.06
     unserem
    0.06
    Act Density 0.006%

    No Known Activations