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

    Neuronpedia

    INDEX
    Explanations

    anything

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    codes
    -0.06
    ingular
    -0.06
     �
    -0.06
    Profit
    -0.06
     now
    -0.06
     fors
    -0.06
     vững
    -0.06
    [first
    -0.06
     totals
    -0.05
    POSITIVE LOGITS
    >Action
    0.07
     Rays
    0.07
     roam
    0.07
    bage
    0.07
     tego
    0.06
     ach
    0.06
     swirling
    0.06
    рай
    0.06
     fingert
    0.06
    _miss
    0.06
    Act Density 0.001%

    No Known Activations