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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /*
    -0.06
    irmware
    -0.06
     가정
    -0.06
     frontier
    -0.06
     chapters
    -0.06
    การใช
    -0.06
    raci
    -0.06
    _TER
    -0.06
    506
    -0.06
    Wis
    -0.06
    POSITIVE LOGITS
     nylon
    0.07
     goats
    0.07
     مهد
    0.07
    episode
    0.07
     �
    0.06
    鐘
    0.06
    ITOR
    0.06
     OnCollision
    0.06
    _COMPILER
    0.06
     disrupted
    0.06
    Act Density 0.072%

    No Known Activations