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

    Neuronpedia

    INDEX
    Explanations

    manners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incluso
    -0.06
    Trace
    -0.06
    (%
    -0.06
    ارهای
    -0.06
     marking
    -0.06
     Seeds
    -0.06
     свя
    -0.06
     hu
    -0.06
    ़
    -0.06
     switch
    -0.06
    POSITIVE LOGITS
     manner
    0.06
    checker
    0.06
    .syntax
    0.06
     filmer
    0.06
    youtu
    0.06
     MIME
    0.06
    miner
    0.06
    urniture
    0.06
    Mitch
    0.06
    .Cursors
    0.06
    Act Density 0.024%

    No Known Activations