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

    Neuronpedia

    INDEX
    Explanations

    track record

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aries
    -0.10
    inke
    -0.10
    ously
    -0.10
    alties
    -0.10
    cue
    -0.10
    akash
    -0.09
    airy
    -0.09
    orest
    -0.09
    er
    -0.09
    oksen
    -0.09
    POSITIVE LOGITS
     record
    0.20
    side
    0.17
    -record
    0.16
    record
    0.15
     Record
    0.14
     track
    0.13
    (track
    0.13
    .Track
    0.13
    Record
    0.13
    lements
    0.13
    Act Density 0.005%

    No Known Activations