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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amelia
    -0.07
     meant
    -0.07
    ันได
    -0.06
    Ven
    -0.06
    /groups
    -0.06
    (rot
    -0.06
    Improved
    -0.06
     premiere
    -0.06
     DRM
    -0.06
     titul
    -0.06
    POSITIVE LOGITS
    eft
    0.07
     Started
    0.07
     거
    0.06
     Shot
    0.06
    USE
    0.06
    apt
    0.06
    _then
    0.06
    τικα
    0.06
     の
    0.06
    (DB
    0.06
    Act Density 0.002%

    No Known Activations