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

    Neuronpedia

    INDEX
    Explanations

    easy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    internal
    -0.07
    apeut
    -0.06
     missiles
    -0.06
    271
    -0.06
    aus
    -0.06
    Arch
    -0.06
    -required
    -0.06
     Rape
    -0.06
    labs
    -0.06
    agents
    -0.06
    POSITIVE LOGITS
     Garcia
    0.06
    Clr
    0.06
    $type
    0.06
    ToggleButton
    0.06
    Much
    0.06
     груз
    0.06
     účin
    0.06
    osy
    0.06
     tô
    0.06
     система
    0.06
    Act Density 0.202%

    No Known Activations