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

    Neuronpedia

    INDEX
    Explanations

    past tense "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _performance
    -0.06
    "?>↵
    -0.06
    _energy
    -0.06
     "),↵
    -0.06
    urvey
    -0.06
    .recv
    -0.06
    .DateTimePicker
    -0.06
    asters
    -0.06
     ctr
    -0.06
     crane
    -0.06
    POSITIVE LOGITS
     hairs
    0.07
     Arabia
    0.06
     Noah
    0.06
     Ens
    0.06
    *****/↵
    0.06
    .Syntax
    0.06
       ↵    ↵
    0.06
     {↵↵↵↵
    0.06
     experi
    0.06
     densely
    0.06
    Act Density 0.068%

    No Known Activations