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

    Neuronpedia

    INDEX
    Explanations

    Technical instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esity
    -0.07
    رانی
    -0.06
    Save
    -0.06
    oid
    -0.06
     pře
    -0.06
    adığı
    -0.06
    _PG
    -0.06
    STOP
    -0.05
    temps
    -0.05
     Fi
    -0.05
    POSITIVE LOGITS
     بالق
    0.07
    갑
    0.07
    ицин
    0.07
     dryer
    0.07
     revoked
    0.07
     conclus
    0.06
     chim
    0.06
     trimmed
    0.06
     voxel
    0.06
     made
    0.06
    Act Density 0.002%

    No Known Activations