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

    Neuronpedia

    INDEX
    Explanations

    list items. headings. entities. concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KeyboardView
    0.56
     necessari
    0.52
    نګه
    0.52
    ANGMAR
    0.50
    Phir
    0.50
    ртуа
    0.48
    AsUpIndicator
    0.48
     shabd
    0.47
     मैनेजमेंट
    0.46
    Malay
    0.46
    POSITIVE LOGITS
    on
    0.64
    _
    0.60
    ra
    0.55
    ation
    0.53
    ar
    0.53
    label
    0.51
    al
    0.51
    ுக்கு
    0.51
    er
    0.50
    ber
    0.50
    Act Density 0.000%

    No Known Activations