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

    Neuronpedia

    INDEX
    Explanations

    importance of value and ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ut
    0.86
    IA
    0.81
    el
    0.72
    ent
    0.70
    ור
    0.70
    ര്‍ക്കും
    0.70
    AS
    0.67
    itiva
    0.64
    jb
    0.64
    information
    0.63
    POSITIVE LOGITS
    ↵
    0.84
    ทำงาน
    0.75
     иметь
    0.74
    จะเป็น
    0.72
    ด
    0.71
     anabolic
    0.70
     Importantly
    0.69
    殤
    0.68
     Interfaith
    0.68
     firef
    0.68
    Act Density 0.090%

    No Known Activations