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

    Neuronpedia

    INDEX
    Explanations

    remaining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intuit
    -0.07
    _Abstract
    -0.07
     invoke
    -0.07
     State
    -0.07
    .activity
    -0.07
     IC
    -0.07
     Ansi
    -0.07
    urface
    -0.06
     thorough
    -0.06
     wave
    -0.06
    POSITIVE LOGITS
     remaining
    0.07
    .remaining
    0.07
     loneliness
    0.07
    经理
    0.07
     जन
    0.06
     군
    0.06
    řen
    0.06
    avern
    0.06
     اقتص
    0.06
    asionally
    0.06
    Act Density 0.009%

    No Known Activations