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

    Neuronpedia

    INDEX
    Explanations

    dates with 3 or 4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -script
    -0.07
    圣
    -0.07
    613
    -0.07
    迹
    -0.07
    -links
    -0.06
    Pok
    -0.06
    unn
    -0.06
     ritual
    -0.06
     Jain
    -0.06
     Naturally
    -0.06
    POSITIVE LOGITS
    OLTIP
    0.07
     cohort
    0.07
     catchy
    0.06
     kuk
    0.06
    续
    0.06
     HRESULT
    0.06
    ($)
    0.06
     AndAlso
    0.06
     abilities
    0.06
     başlamış
    0.06
    Act Density 0.029%

    No Known Activations