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

    Neuronpedia

    INDEX
    Explanations

    dining room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TRACK
    0.57
    cle
    0.57
     PARTIC
    0.56
    バ
    0.55
    지
    0.55
    K
    0.54
     GRADE
    0.53
    M
    0.52
    ונ
    0.51
    Tracks
    0.51
    POSITIVE LOGITS
     Puj
    0.54
     rusak
    0.54
    oxet
    0.52
     namani
    0.52
    ...@
    0.51
    ...”
    0.51
     buty
    0.50
    $...
    0.50
     orator
    0.49
     unf
    0.49
    Act Density 0.000%

    No Known Activations