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

    Neuronpedia

    INDEX
    Explanations

    options and defaults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ាត់
    0.45
    overlaps
    0.45
    ête
    0.44
    ivesse
    0.44
     повторя
    0.44
    otiti
    0.44
    ellus
    0.44
    SpringMVCProject
    0.44
    ccnc
    0.43
    SqlCommand
    0.43
    POSITIVE LOGITS
     option
    0.82
    选择
    0.81
     options
    0.80
     choice
    0.77
     default
    0.76
    を選択
    0.75
    选项
    0.73
     선택
    0.73
     selectable
    0.72
     keuze
    0.71
    Act Density 0.353%

    No Known Activations