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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canaria
    -0.52
     Италијани
    -0.52
    .@
    -0.50
     writable
    -0.50
    })`
    -0.49
    .";
    -0.49
    httphttps
    -0.49
     архивлан
    -0.48
    :@
    -0.48
    SearchParams
    -0.48
    POSITIVE LOGITS
     who
    0.63
     насељу
    0.56
    imageio
    0.55
    TabLayout
    0.54
    IntoConstraints
    0.54
    OGND
    0.53
    XmlAccessType
    0.50
    abbix
    0.50
    ApiModelProperty
    0.49
     noticing
    0.48
    Act Density 0.001%

    No Known Activations