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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </thead>
    -0.64
    AndEndTag
    -0.57
     createSlice
    -0.56
    RTEX
    -0.53
     cref
    -0.51
    randir
    -0.51
    ConstraintLayout
    -0.50
     Yani
    -0.48
    ########.
    -0.48
    cely
    -0.48
    POSITIVE LOGITS
     square
    0.65
     HasFactory
    0.60
    (&:
    0.57
     imaginary
    0.56
     sphere
    0.54
    WebVitals
    0.53
     life
    0.52
     Gilmour
    0.52
     Square
    0.50
     "..\..\..\
    0.49
    Act Density 0.002%

    No Known Activations