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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⇨
    -0.08
     безопас
    -0.07
    𝐲
    -0.07
     Spinner
    -0.07
    ighbors
    -0.07
    Perform
    -0.06
    将持续
    -0.06
     relacion
    -0.06
     nơi
    -0.06
    .ceil
    -0.06
    POSITIVE LOGITS
    _soup
    0.07
    (Gtk
    0.07
    _Create
    0.07
     Kickstarter
    0.07
    _kel
    0.06
    י�
    0.06
    ἔ
    0.06
    둥
    0.06
     dean
    0.06
    marca
    0.06
    Act Density 0.001%

    No Known Activations