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

    Neuronpedia

    INDEX
    Explanations

    held

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mix
    -0.07
     jurors
    -0.07
     referring
    -0.07
     pickups
    -0.07
     cassette
    -0.07
     meal
    -0.07
     meanwhile
    -0.06
     підприємств
    -0.06
     accountability
    -0.06
     resta
    -0.06
    POSITIVE LOGITS
     lanc
    0.07
     Isaiah
    0.07
    _crc
    0.07
     الاح
    0.06
    Aj
    0.06
     Kis
    0.06
    fclose
    0.06
    -first
    0.06
    侵
    0.06
     Cir
    0.06
    Act Density 0.000%

    No Known Activations