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

    Neuronpedia

    INDEX
    Explanations

    key strategic points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.71
     standout
    0.70
    ר
    0.70
    0
    0.70
     loro
    0.67
     harrowing
    0.63
    2
    0.63
    al
    0.62
     dialogue
    0.62
    ی
    0.62
    POSITIVE LOGITS
    猀
    0.62
    𝐜
    0.61
     დროს
    0.61
     Kräfte
    0.61
    బర్
    0.60
    áme
    0.60
    人不
    0.58
    ве
    0.57
    вано
    0.57
    悎
    0.57
    Act Density 0.009%

    No Known Activations