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

    Neuronpedia

    INDEX
    Explanations

    weeks and days calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.55
    mathbf
    0.48
    explored
    0.47
    error
    0.47
    how
    0.47
    üler
    0.47
    o
    0.47
    info
    0.46
    infested
    0.46
    erreur
    0.45
    POSITIVE LOGITS
     Airl
    0.47
     Dialogue
    0.46
    铨
    0.46
    汰
    0.45
     Reconciliation
    0.44
     Bingo
    0.44
     শার
    0.43
     DIA
    0.43
    拃
    0.43
     DI
    0.42
    Act Density 0.003%

    No Known Activations