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

    Neuronpedia

    INDEX
    Explanations

    explaining about abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Which
    0.65
    which
    0.54
     duquel
    0.51
     Which
    0.49
    Others
    0.48
     suivantes
    0.47
     которой
    0.47
    Unknown
    0.47
    יים
    0.47
    只有一个
    0.47
    POSITIVE LOGITS
     about
    0.76
     remediation
    0.71
     teamwork
    0.70
     how
    0.68
     storytelling
    0.68
     vandalism
    0.66
     tantamount
    0.64
     heartwarming
    0.64
     akin
    0.64
     indicative
    0.63
    Act Density 0.632%

    No Known Activations