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

    Neuronpedia

    INDEX
    Explanations

    complete the conversation or story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     problemy
    0.45
    ᕋ
    0.43
     Hussein
    0.43
    UserRepository
    0.41
     problémy
    0.41
    ovation
    0.41
    𒁁
    0.40
     Sebasti
    0.39
    Ἡ
    0.39
    sobre
    0.39
    POSITIVE LOGITS
     add
    0.62
    add
    0.52
     Add
    0.49
    ’
    0.46
    Add
    0.46
     extras
    0.45
     additives
    0.44
     addons
    0.43
     additive
    0.43
    完成后
    0.43
    Act Density 0.002%

    No Known Activations