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

    Neuronpedia

    INDEX
    Explanations

    chips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iddia
    -0.07
    	an
    -0.07
     Jahren
    -0.06
    mai
    -0.06
     Directive
    -0.06
     provád
    -0.06
     forte
    -0.06
     amour
    -0.06
     hockey
    -0.06
    naires
    -0.06
    POSITIVE LOGITS
    IRQ
    0.07
    ,module
    0.06
    atrigesimal
    0.06
    .EXIT
    0.06
    创新
    0.06
     Chips
    0.06
    _xlabel
    0.06
     unmist
    0.06
    !(↵
    0.06
    breaking
    0.06
    Act Density 0.004%

    No Known Activations