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

    Neuronpedia

    INDEX
    Explanations

    air dry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Also
    0.47
    both
    0.42
     பகுதியில்
    0.41
    and
    0.41
     both
    0.41
     Also
    0.40
    also
    0.40
     അദ്ദേഹ
    0.39
     এটাও
    0.39
     également
    0.38
    POSITIVE LOGITS
     strive
    0.60
     striving
    0.60
     તેઓ
    0.56
    いずれ
    0.54
     তারা
    0.54
     стрем
    0.53
    他们
    0.52
    追求
    0.52
     strives
    0.51
    それぞれ
    0.51
    Act Density 0.002%

    No Known Activations