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

    Neuronpedia

    INDEX
    Explanations

    log probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dishon
    0.42
     intraven
    0.38
     árv
    0.35
     d
    0.35
     daqu
    0.35
    惯
    0.35
     obstructions
    0.35
    젼
    0.35
    ramethyl
    0.35
     quente
    0.35
    POSITIVE LOGITS
                                   
    0.58
    0.47
    <b>
    0.42
    0.41
    ></
    0.39
    0.39
    0.39
    <strong>
    0.39
    öse
    0.38
                                 
    0.38
    Act Density 0.018%

    No Known Activations