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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [['
    -0.07
     aisle
    -0.07
    rams
    -0.06
    ité
    -0.06
    NIC
    -0.06
    izable
    -0.06
    Trip
    -0.06
     writeTo
    -0.06
     twist
    -0.06
    』（
    -0.06
    POSITIVE LOGITS
    bij
    0.07
     follow
    0.06
     describe
    0.06
     �
    0.06
     Category
    0.06
    .xlabel
    0.06
    _scale
    0.06
    cause
    0.06
    (pointer
    0.06
    .getPosition
    0.06
    Act Density 0.066%

    No Known Activations