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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (segment
    -0.07
     sens
    -0.07
     deformation
    -0.06
     strikeouts
    -0.06
    .xrTableCell
    -0.06
    _CONFIRM
    -0.06
    -ren
    -0.06
     decreased
    -0.06
    _maps
    -0.06
    _outputs
    -0.06
    POSITIVE LOGITS
     Eat
    0.07
     бал
    0.07
     Valle
    0.06
    ALL
    0.06
    unter
    0.06
     něco
    0.06
     nám
    0.06
     specialties
    0.06
    all
    0.06
     Unters
    0.06
    Act Density 0.001%

    No Known Activations