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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loving
    -0.07
    41
    -0.07
     Command
    -0.07
     Licensing
    -0.06
     command
    -0.06
    prices
    -0.06
     looming
    -0.06
     Cologne
    -0.06
     crossorigin
    -0.06
    ircles
    -0.06
    POSITIVE LOGITS
    datos
    0.06
    Ж
    0.06
    WEEN
    0.06
     heed
    0.06
    *>*
    0.06
     وكانت
    0.06
     Aura
    0.06
     трав
    0.06
    =&
    0.06
     마법
    0.06
    Act Density 0.013%

    No Known Activations