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

    Neuronpedia

    INDEX
    Explanations

    evaluating advantages or shortcomings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    berger
    0.40
    하는
    0.39
    ','')
    0.38
    hilfe
    0.37
    르
    0.37
    专注
    0.36
    처럼
    0.36
    istar
    0.36
    考える
    0.36
    ResultMessage
    0.36
    POSITIVE LOGITS
     Finances
    0.49
     finances
    0.47
     cuisine
    0.44
     lack
    0.42
     lacks
    0.42
     shortcomings
    0.41
     apparence
    0.41
    缺乏
    0.40
     horribly
    0.40
     shitty
    0.40
    Act Density 0.133%

    No Known Activations