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

    Neuronpedia

    INDEX
    Explanations

    references to present time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cos
    -0.07
     لن
    -0.07
     certain
    -0.06
    ssh
    -0.06
    -enter
    -0.06
     eager
    -0.06
    	se
    -0.06
    725
    -0.06
    iever
    -0.06
    ouched
    -0.06
    POSITIVE LOGITS
    矢
    0.07
     Exist
    0.07
     Afghan
    0.06
    anal
    0.06
     Revenge
    0.06
    Vue
    0.06
    datos
    0.06
    .reset
    0.06
     método
    0.06
     getIntent
    0.06
    Act Density 0.015%

    No Known Activations