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

    Neuronpedia

    INDEX
    Explanations

    display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     patent
    -0.07
    iene
    -0.07
     Macron
    -0.06
    _auc
    -0.06
     Malik
    -0.06
    pires
    -0.06
     Teeth
    -0.06
    _COUNTER
    -0.06
    kte
    -0.06
    igure
    -0.06
    POSITIVE LOGITS
     display
    0.08
     dbg
    0.07
    .EXIT
    0.06
     pulmonary
    0.06
    Getty
    0.06
    Г
    0.06
    だろう
    0.06
     Do
    0.06
     dig
    0.06
     tempting
    0.06
    Act Density 0.007%

    No Known Activations