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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polygons
    -0.07
     vals
    -0.07
     sponge
    -0.06
     yr
    -0.06
    .exe
    -0.06
    ("");↵
    -0.06
    .Statement
    -0.06
    (gs
    -0.06
     Trout
    -0.06
     Summary
    -0.06
    POSITIVE LOGITS
     асп
    0.07
     confirmPassword
    0.06
     fierce
    0.06
    (userData
    0.06
     hydr
    0.06
    BSD
    0.06
    ováno
    0.06
    udd
    0.06
    moid
    0.06
    0.06
    Act Density 0.108%

    No Known Activations