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

    Neuronpedia

    INDEX
    Explanations

    Logic and theorems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transformers
    -0.08
    机电
    -0.08
    \Models
    -0.07
     đã
    -0.07
    解脱
    -0.07
     FirebaseFirestore
    -0.07
    maal
    -0.07
    地坪
    -0.07
    两家
    -0.07
    ציל
    -0.06
    POSITIVE LOGITS
    竞争
    0.07
    OP
    0.07
    اس
    0.06
    ﲻ
    0.06
    おります
    0.06
     match
    0.06
    umpy
    0.06
    за
    0.06
     signalling
    0.06
    _preview
    0.06
    Act Density 0.003%

    No Known Activations