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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caesar
    -0.08
     guerra
    -0.07
     volunt
    -0.07
    becue
    -0.07
    teness
    -0.07
    _capacity
    -0.07
    _Render
    -0.07
    ilk
    -0.07
    恓
    -0.07
     Generate
    -0.07
    POSITIVE LOGITS
    lator
    0.07
    $↵
    0.07
     Mig
    0.06
     Fishing
    0.06
    .datasource
    0.06
    נטר
    0.06
     partnering
    0.06
    柄
    0.06
     appearances
    0.06
    ?”
    0.06
    Act Density 0.000%

    No Known Activations