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

    Neuronpedia

    INDEX
    Explanations

    incoming/outgoing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bras
    -0.28
    Off
    -0.27
    inct
    -0.27
    åĤį
    -0.25
     bem
    -0.25
    dis
    -0.25
     constants
    -0.25
    åIJ©
    -0.25
     Dis
    -0.25
    aven
    -0.25
    POSITIVE LOGITS
    åºĶçĶ¨æŁ¥çľĭ
    0.26
     LGPL
    0.26
    EGIN
    0.26
     Guth
    0.25
    olland
    0.25
     Scri
    0.24
    客æłĪ
    0.24
     fault
    0.24
    pell
    0.24
    callbacks
    0.24
    Act Density 2.340%

    No Known Activations