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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ican
    -0.07
     Niagara
    -0.07
     fewer
    -0.07
     HomeComponent
    -0.06
     decline
    -0.06
     Kitty
    -0.06
     Explorer
    -0.06
    _OBJ
    -0.06
    ossa
    -0.06
     Commerce
    -0.06
    POSITIVE LOGITS
    .commands
    0.06
    ايا
    0.06
     sống
    0.06
    лич
    0.06
     recursively
    0.06
    ريس
    0.06
    metis
    0.06
    スレ
    0.05
     математи
    0.05
     hear
    0.05
    Act Density 0.029%

    No Known Activations