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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marines
    -0.07
     renewal
    -0.07
     Mothers
    -0.06
     dialogs
    -0.06
    Even
    -0.06
     téléphone
    -0.06
    “If
    -0.06
     journeys
    -0.06
     Est
    -0.06
    _transactions
    -0.06
    POSITIVE LOGITS
     соп
    0.07
    scar
    0.07
    patch
    0.07
    /ac
    0.06
    =@
    0.06
    221
    0.06
    enter
    0.06
    #{@
    0.06
    []={
    0.06
    ραση
    0.06
    Act Density 0.009%

    No Known Activations