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

    Neuronpedia

    INDEX
    Explanations

    video clip or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Found
    0.68
    Focus
    0.60
    Find
    0.59
    Fifty
    0.59
    Five
    0.57
     Fakat
    0.57
    As
    0.56
    Ne
    0.56
    found
    0.56
    Ma
    0.56
    POSITIVE LOGITS
    等は
    0.59
    によっては
    0.58
    /
    0.56
     alike
    0.56
     libertad
    0.55
     документів
    0.53
    )}
    0.52
    される
    0.52
     accretion
    0.51
    ങ്ക്
    0.51
    Act Density 0.523%

    No Known Activations