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

    Neuronpedia

    INDEX
    Explanations

    Legal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MessageType
    -0.07
     Holmes
    -0.07
     Core
    -0.07
     poles
    -0.07
    _mono
    -0.07
     itself
    -0.06
    N
    -0.06
    _HINT
    -0.06
    imations
    -0.06
     owes
    -0.06
    POSITIVE LOGITS
    �
    0.06
     bridal
    0.06
    EVER
    0.06
    Chat
    0.06
    .signup
    0.06
    GeneratedValue
    0.06
    PullParser
    0.06
    .didReceiveMemoryWarning
    0.06
     مسجد
    0.06
    $values
    0.06
    Act Density 0.011%

    No Known Activations