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

    Neuronpedia

    INDEX
    Explanations

    iciency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (round
    -0.08
    ække
    -0.07
    (Collections
    -0.06
    levation
    -0.06
    ,strlen
    -0.06
    _UP
    -0.06
     ridicule
    -0.06
    avic
    -0.06
    TRIES
    -0.06
    Contin
    -0.06
    POSITIVE LOGITS
     نمونه
    0.07
     Corn
    0.07
    voir
    0.07
    .edu
    0.07
     "
    0.07
    −
    0.07
    alarından
    0.06
    ,'"
    0.06
     harness
    0.06
    Harness
    0.06
    Act Density 0.000%

    No Known Activations