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

    Neuronpedia

    INDEX
    Explanations

    curriculum and syllabus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ীবন
    0.74
    스
    0.74
    ITCH
    0.72
    ᠶ
    0.71
    heartedly
    0.70
    hearted
    0.69
     hearted
    0.69
    אנ
    0.69
    notch
    0.67
    mdash
    0.67
    POSITIVE LOGITS
    bouw
    0.78
    dling
    0.68
     needlessly
    0.67
    ']=$
    0.66
    FBSDKError
    0.66
     thuyết
    0.65
     seria
    0.64
     sejam
    0.64
     теми
    0.64
    ဟုတ်
    0.64
    Act Density 0.059%

    No Known Activations