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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ->{
    -0.07
     RPM
    -0.07
     xf
    -0.06
     Jeh
    -0.06
    Cod
    -0.06
     Military
    -0.06
     overridden
    -0.06
     integration
    -0.06
    .jd
    -0.06
     باید
    -0.06
    POSITIVE LOGITS
     inches
    0.08
    dropIfExists
    0.07
     sophomore
    0.07
     molding
    0.07
    .ACCESS
    0.06
     drug
    0.06
     SIN
    0.06
     meter
    0.06
    _age
    0.06
    389
    0.06
    Act Density 0.031%

    No Known Activations