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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pts
    -0.07
     plants
    -0.07
    CONDS
    -0.06
     ////
    -0.06
    opez
    -0.06
     devised
    -0.06
     dend
    -0.06
     CONTROL
    -0.06
    633
    -0.06
     نوشته
    -0.06
    POSITIVE LOGITS
     Mega
    0.07
    itra
    0.07
     اخت
    0.06
     丶
    0.06
    .Connection
    0.06
    zell
    0.06
    0.06
     profoundly
    0.06
    )(
    0.06
     aracılığıyla
    0.06
    Act Density 0.007%

    No Known Activations