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

    Neuronpedia

    INDEX
    Explanations

    Transportation tickets/passes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piercing
    -0.08
     Prison
    -0.07
     doe
    -0.07
    ,X
    -0.07
    =date
    -0.07
     mare
    -0.07
     Empty
    -0.06
     Orlando
    -0.06
     Armor
    -0.06
    事发
    -0.06
    POSITIVE LOGITS
    蓓
    0.07
    amura
    0.07
    airobi
    0.07
    _partial
    0.07
    🥕
    0.07
    相应的
    0.07
     Cameron
    0.07
     Moderator
    0.07
    📻
    0.07
    エステ
    0.06
    Act Density 0.020%

    No Known Activations