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

    Neuronpedia

    INDEX
    Explanations

    VPN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Hello
    -0.07
     pelos
    -0.07
    ost
    -0.07
    يث
    -0.07
     الأك
    -0.06
    ันอ
    -0.06
     acidic
    -0.06
     backlash
    -0.06
    ']='
    -0.06
     Piet
    -0.06
    POSITIVE LOGITS
    Hidden
    0.07
    VPN
    0.07
     topical
    0.06
    _Sub
    0.06
    gren
    0.06
    TV
    0.06
    violent
    0.06
     Hidden
    0.06
    支援
    0.06
     Saga
    0.06
    Act Density 0.003%

    No Known Activations