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

    Neuronpedia

    INDEX
    Explanations

    identify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -detail
    -0.06
    .ll
    -0.06
     rings
    -0.06
    laws
    -0.06
    choice
    -0.06
     install
    -0.06
     add
    -0.06
    Group
    -0.06
    <Box
    -0.06
     Routine
    -0.06
    POSITIVE LOGITS
     identified
    0.10
     identifies
    0.08
     Identified
    0.08
     identify
    0.08
     identifying
    0.07
    >true
    0.07
     TKey
    0.07
     Mayıs
    0.07
     Gene
    0.06
    _PRI
    0.06
    Act Density 0.031%

    No Known Activations