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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ServletRequest
    -0.07
     Emma
    -0.07
     -----
    -0.06
    ----------------
    -0.06
     proud
    -0.06
     engel
    -0.06
     fruitful
    -0.06
    ือ
    -0.06
    authentication
    -0.06
    ------------
    -0.06
    POSITIVE LOGITS
    نه
    0.07
    _NEG
    0.06
     spills
    0.06
    lah
    0.06
    aremos
    0.06
     dejar
    0.06
    Preference
    0.06
    ürn
    0.06
    expert
    0.06
    .PrimaryKey
    0.06
    Act Density 0.091%

    No Known Activations