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

    Neuronpedia

    INDEX
    Explanations

    single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -visible
    -0.07
    Friends
    -0.07
     brothers
    -0.07
    unc
    -0.07
    ющие
    -0.07
    rin
    -0.07
    ingt
    -0.07
    و
    -0.07
     pictures
    -0.06
    lerden
    -0.06
    POSITIVE LOGITS
    .Adapter
    0.06
    　ｌ
    0.06
     midfield
    0.06
    BootTest
    0.06
     odst
    0.06
     renovated
    0.06
     prostitute
    0.06
     hasNext
    0.06
    $instance
    0.06
     renov
    0.06
    Act Density 0.001%

    No Known Activations