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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.77
    abestanden
    -0.76
     Signalez
    -0.74
    SequentialGroup
    -0.73
     pinulongan
    -0.72
    TagMode
    -0.70
     >=",
    -0.69
     مشين
    -0.69
    awtextra
    -0.68
    LookAnd
    -0.66
    POSITIVE LOGITS
     varandra
    0.51
     sekali
    0.48
     dieux
    0.45
     prácti
    0.44
     Golden
    0.44
     Gold
    0.43
     vägen
    0.42
     êtres
    0.39
     démocr
    0.39
    light
    0.38
    Act Density 0.002%

    No Known Activations