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

    Neuronpedia

    INDEX
    Explanations

    suggested actions or recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    邁
    0.39
    都需要
    0.36
    を楽し
    0.35
     beneficia
    0.35
     முடியும்
    0.34
    を受
    0.34
     discriminant
    0.34
     அனுப
    0.34
     받을
    0.33
     потребу
    0.33
    POSITIVE LOGITS
     whisk
    0.58
     suggest
    0.55
     suggested
    0.53
     recommend
    0.50
    suggest
    0.48
     Suggested
    0.47
     recommended
    0.46
     remind
    0.46
     vorgesch
    0.46
     tweaked
    0.44
    Act Density 0.009%

    No Known Activations