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

    Neuronpedia

    INDEX
    Explanations

    characters following letter codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    óle
    0.67
    eword
    0.66
    ífer
    0.56
    cameraId
    0.56
    ూర్
    0.55
    BleStatus
    0.54
    thisTrack
    0.53
    lifestyle
    0.53
    bevel
    0.53
    ग्वि
    0.53
    POSITIVE LOGITS
     Lo
    0.59
     Kombination
    0.59
     M
    0.56
     S
    0.56
     Amenities
    0.56
     s
    0.55
     d
    0.55
     Teen
    0.55
     N
    0.54
     James
    0.53
    Act Density 0.010%

    No Known Activations