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

    Neuronpedia

    INDEX
    Explanations

    complex vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baffled
    -0.71
    da
    -0.51
    appan
    -0.50
     puzzled
    -0.50
    msa
    -0.47
    aware
    -0.46
     Kem
    -0.46
    パ
    -0.45
    bruck
    -0.45
     Rack
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.78
    TagMode
    0.74
    tvguidetime
    0.71
    IUrlHelper
    0.69
    存于互联网档案馆
    0.68
     betweenstory
    0.65
     ModelExpression
    0.65
     titolata
    0.63
    Sucesor
    0.63
     Theſe
    0.62
    Act Density 1.470%

    No Known Activations