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

    Neuronpedia

    INDEX
    Explanations

    visits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     births
    -0.07
    attack
    -0.07
    Parse
    -0.07
     proprietor
    -0.07
     bitmask
    -0.07
    _true
    -0.06
     CITY
    -0.06
    -zone
    -0.06
    èm
    -0.06
    icio
    -0.06
    POSITIVE LOGITS
    ổi
    0.06
     Sentence
    0.06
     essay
    0.06
     sag
    0.06
     Intent
    0.06
     blows
    0.06
     hoe
    0.06
     shale
    0.06
    Summon
    0.06
    .disc
    0.06
    Act Density 0.018%

    No Known Activations