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

    Neuronpedia

    INDEX
    Explanations

    knife

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dut
    -0.08
    欣
    -0.06
     extensive
    -0.06
     upd
    -0.06
    Henry
    -0.06
    ?\
    -0.06
    ολ
    -0.06
    _company
    -0.06
     země
    -0.06
        ↵    ↵    ↵
    -0.06
    POSITIVE LOGITS
     sword
    0.08
     knife
    0.08
    azaar
    0.07
    grily
    0.07
     Knife
    0.07
    OfYear
    0.07
     CID
    0.07
     façon
    0.07
    joining
    0.07
    alers
    0.07
    Act Density 0.062%

    No Known Activations