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

    Neuronpedia

    INDEX
    Explanations

    need to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zur
    -0.11
    indo
    -0.11
    uther
    -0.10
    ToStr
    -0.09
    earer
    -0.09
    alice
    -0.09
     Raq
    -0.09
     kepada
    -0.09
     XCT
    -0.09
    aldi
    -0.09
    POSITIVE LOGITS
    lessly
    0.22
    n
    0.17
     to
    0.17
    (ed
    0.15
    iest
    0.11
    /w
    0.11
    iness
    0.11
    led
    0.11
    çļĦæĺ¯
    0.10
    ding
    0.10
    Act Density 0.028%

    No Known Activations