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

    Neuronpedia

    INDEX
    Explanations

    to + verb or noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     if
    -1.75
    Surprisingly
    -1.46
    氾
    -1.41
    Everything
    -1.41
     provides
    -1.35
    Just
    -1.31
    All
    -1.31
     this
    -1.30
     helps
    -1.28
    What
    -1.27
    POSITIVE LOGITS
    necessarily
    1.45
    <tr>
    1.40
    螃
    1.35
     effectué
    1.34
    嚒
    1.31
    摸了
    1.30
     छोड़
    1.29
     asfal
    1.29
     appelée
    1.27
     associée
    1.26
    Act Density 0.017%

    No Known Activations