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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exploration
    -0.08
    230
    -0.07
    Gb
    -0.07
    branch
    -0.06
    gett
    -0.06
     wor
    -0.06
    =',
    -0.06
    udget
    -0.06
    ='<
    -0.06
    妇
    -0.06
    POSITIVE LOGITS
    (lhs
    0.06
    itized
    0.06
    {EIF
    0.06
    font
    0.06
    .Init
    0.06
     violate
    0.06
    neys
    0.06
    Illegal
    0.06
     उसन
    0.06
    ）は
    0.05
    Act Density 0.063%

    No Known Activations