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

    Neuronpedia

    INDEX
    Explanations

    problem/solution and scoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ých
    0.52
    zeigt
    0.52
    wbr
    0.50
    льних
    0.50
     Bedingungen
    0.48
    瞰
    0.47
    mathbb
    0.47
    峀
    0.46
    ntz
    0.46
    Nieder
    0.46
    POSITIVE LOGITS
     errand
    0.55
     the
    0.53
     literacy
    0.52
     formality
    0.51
    '
    0.49
     entry
    0.48
     attendance
    0.47
     du
    0.46
     against
    0.46
     requests
    0.46
    Act Density 0.003%

    No Known Activations