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

    Neuronpedia

    INDEX
    Explanations

    Path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacking
    -0.07
    Oper
    -0.07
     fps
    -0.06
     mailbox
    -0.06
     UIManager
    -0.06
     Thing
    -0.06
    Received
    -0.06
     top
    -0.06
    .drawRect
    -0.06
     Attributes
    -0.06
    POSITIVE LOGITS
     (=
    0.07
     …
    0.06
     vhodné
    0.06
    -results
    0.06
    elerinin
    0.06
    /model
    0.06
    ?
    0.06
    datos
    0.06
    (cube
    0.06
     minul
    0.06
    Act Density 0.007%

    No Known Activations