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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    knowledge
    -0.92
     myſelf
    -0.79
     connaissances
    -0.73
     ainfi
    -0.71
    Knowledge
    -0.69
     Majefty
    -0.68
     knowledge
    -0.68
     aveug
    -0.68
     poffible
    -0.67
     hâte
    -0.66
    POSITIVE LOGITS
    Portale
    0.62
    CopyWith
    0.60
    GenerationType
    0.51
     cortes
    0.49
     переписи
    0.48
     发表于
    0.47
     charge
    0.46
    Instantiation
    0.46
    vek
    0.45
    tvguidetime
    0.45
    Act Density 0.038%

    No Known Activations