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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usu
    -0.07
    laus
    -0.07
     chatt
    -0.07
     Nhĩ
    -0.07
     koş
    -0.07
    _dead
    -0.06
    dj
    -0.06
    setDefault
    -0.06
     hisset
    -0.06
     густ
    -0.06
    POSITIVE LOGITS
     upstream
    0.07
     plaintext
    0.06
     supplementary
    0.06
    ItemType
    0.06
    anical
    0.06
     infer
    0.06
    ArrayList
    0.06
    ич
    0.06
    alive
    0.06
    ύ
    0.06
    Act Density 0.016%

    No Known Activations