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
     grapes
    -0.08
    Task
    -0.07
     Listen
    -0.07
     Task
    -0.07
    612
    -0.07
    meno
    -0.07
    .sec
    -0.07
     discounts
    -0.06
    terminate
    -0.06
     advocate
    -0.06
    POSITIVE LOGITS
     امر
    0.06
    رات
    0.06
    rances
    0.06
    êtes
    0.06
     activist
    0.06
     appellate
    0.06
    EObject
    0.06
     �
    0.06
     třídy
    0.06
     Cait
    0.06
    Act Density 0.003%

    No Known Activations