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

    Neuronpedia

    INDEX
    Explanations

    pt units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.39
    𒁍
    0.39
     Privat
    0.38
     حجت
    0.38
     requestId
    0.37
    āyaṇa
    0.37
    ជ្
    0.37
    езд
    0.36
    °.
    0.35
     Voj
    0.35
    POSITIVE LOGITS
    两天
    0.40
     point
    0.38
     Point
    0.38
     POINT
    0.38
    point
    0.38
    IONAL
    0.38
    deb
    0.37
    PerHour
    0.37
    אים
    0.37
    ional
    0.37
    Act Density 0.000%

    No Known Activations