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

    Neuronpedia

    INDEX
    Explanations

    misdiagnosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     become
    -0.07
    _ORD
    -0.06
     useful
    -0.06
    ไฟ
    -0.06
    _PRODUCT
    -0.06
    .normal
    -0.06
     touching
    -0.06
     playable
    -0.06
    水
    -0.05
    -largest
    -0.05
    POSITIVE LOGITS
    OUNDS
    0.07
     зрения
    0.07
    voke
    0.07
    sets
    0.07
     дает
    0.06
     puck
    0.06
    _spi
    0.06
    _PWR
    0.06
    ftp
    0.06
    yn
    0.06
    Act Density 0.024%

    No Known Activations