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

    Neuronpedia

    INDEX
    Explanations

    list items or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wanted
    0.38
     candidates
    0.37
     coordinator
    0.37
     location
    0.36
     Wanted
    0.36
     Boyer
    0.36
     notification
    0.35
    args
    0.35
     options
    0.35
     different
    0.34
    POSITIVE LOGITS
     behaves
    0.55
     undergoes
    0.52
     lacks
    0.48
     вокруг
    0.48
    缺乏
    0.46
    Sumber
    0.45
     obsahuje
    0.44
    áte
    0.43
     struggles
    0.43
     resonates
    0.43
    Act Density 0.000%

    No Known Activations