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

    Neuronpedia

    INDEX
    Explanations

    transcription

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hâl
    -0.07
    表情
    -0.07
    �
    -0.07
     pile
    -0.06
     explosives
    -0.06
     ди
    -0.06
     최근
    -0.06
     물
    -0.06
    burst
    -0.06
    _ACT
    -0.06
    POSITIVE LOGITS
    cribing
    0.10
     transcription
    0.07
    cribed
    0.07
    cribe
    0.07
     ordained
    0.07
     axiom
    0.07
    нциклопед
    0.06
    (db
    0.06
    ˘
    0.06
     Snackbar
    0.06
    Act Density 0.007%

    No Known Activations