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

    Neuronpedia

    INDEX
    Explanations

    either

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keyboard
    -0.07
            
↵
    -0.07
     hardware
    -0.06
        
↵
    -0.06
    Like
    -0.06
    While
    -0.06
    하면서
    -0.06
     glass
    -0.06
    Do
    -0.06
    Vi
    -0.06
    POSITIVE LOGITS
    려고
    0.06
     clashed
    0.06
    ‐‐
    0.06
     назнач
    0.06
    blers
    0.06
    _share
    0.06
     bozuk
    0.06
    під
    0.06
     Clover
    0.06
     percentage
    0.06
    Act Density 0.001%

    No Known Activations