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

    Neuronpedia

    INDEX
    Explanations

    inner alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     J
    0.76
    J
    0.59
     j
    0.50
    Ｊ
    0.48
    ⱼ
    0.48
     JPMorgan
    0.48
     ജെ
    0.47
     JPL
    0.46
    𝐽
    0.46
     Y
    0.46
    POSITIVE LOGITS
    dcs
    0.39
    ਸ਼ਨ
    0.38
    麦
    0.38
    appy
    0.38
    𒊒
    0.37
    никах
    0.36
    Kenny
    0.36
     Dusty
    0.36
     Gustav
    0.35
    зите
    0.35
    Act Density 0.005%

    No Known Activations