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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     summer
    0.54
     DVD
    0.48
     minimal
    0.47
     ABC
    0.47
     Summer
    0.46
     L
    0.46
     tid
    0.46
     Saturday
    0.45
     Seag
    0.45
    ingleton
    0.45
    POSITIVE LOGITS
    ст
    0.50
    Breed
    0.47
    стром
    0.47
    was
    0.46
    BUY
    0.44
    Come
    0.43
    ній
    0.43
    inception
    0.43
    BY
    0.42
    лук
    0.42
    Act Density 0.011%

    No Known Activations