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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conservancy
    -1.74
     conserv
    -1.01
     Conservatory
    -0.78
    conserv
    -0.77
     CONSERV
    -0.75
     conservatory
    -0.75
     Conserv
    -0.71
    Conserv
    -0.70
    ,$_
    -0.69
    unknownFields
    -0.65
    POSITIVE LOGITS
     Anfitrión
    0.53
     illustrazione
    0.46
     altså
    0.46
    ówczas
    0.45
     prêts
    0.45
     récomp
    0.44
    SuppressMessage
    0.44
     démocr
    0.44
    agot
    0.43
     alltså
    0.43
    Act Density 0.016%

    No Known Activations