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

    Neuronpedia

    INDEX
    Explanations

    like or unlike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gefunden
    0.44
    學者
    0.43
    ർന്ന
    0.41
     stochastic
    0.41
    scribed
    0.41
    spicuous
    0.41
     ながら
    0.40
    ◯
    0.40
     strikingly
    0.39
     n
    0.39
    POSITIVE LOGITS
     unsold
    0.44
    ิจ
    0.43
    juna
    0.42
     স
    0.42
    ستا
    0.42
    超级
    0.41
     детали
    0.39
     жало
    0.38
     معاش
    0.38
     откло
    0.36
    Act Density 0.010%

    No Known Activations