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

    Neuronpedia

    INDEX
    Explanations

    planning and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indeed
    0.50
    ť
    0.49
    Indeed
    0.48
    antec
    0.47
    ają
    0.46
     indeed
    0.45
    ika
    0.42
    ikes
    0.40
    ksi
    0.40
    ans
    0.39
    POSITIVE LOGITS
     equates
    0.49
    ᾶ
    0.44
     exo
    0.44
     uncovered
    0.43
     see
    0.42
     achievable
    0.41
     reaper
    0.41
     arranged
    0.41
     reveal
    0.41
     uncover
    0.41
    Act Density 0.001%

    No Known Activations