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

    Neuronpedia

    INDEX
    Explanations

    grocery list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ul
    0.54
    ta
    0.52
    at
    0.49
    //
    0.47
    na
    0.46
     해서
    0.46
    ants
    0.45
     сосе
    0.44
    ator
    0.44
    ций
    0.44
    POSITIVE LOGITS
     impossibility
    0.46
     GOODS
    0.46
     mand
    0.45
    ր
    0.44
     nightmare
    0.44
     voluntary
    0.44
    Sharma
    0.43
     opak
    0.43
     items
    0.43
     fireplace
    0.43
    Act Density 0.000%

    No Known Activations