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

    Neuronpedia

    INDEX
    Explanations

    VTuber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    呆
    0.63
     डॉन
    0.60
     اسرائی
    0.59
    聃
    0.59
    ंकिंग
    0.58
     isTestSource
    0.57
    BuildAction
    0.57
    শোধ
    0.57
    भाष
    0.56
     ornare
    0.56
    POSITIVE LOGITS
    V
    2.97
     V
    2.90
    Ｖ
    2.63
    v
    2.38
     VC
    2.34
     v
    2.31
    VM
    2.28
    VC
    2.27
    𝑉
    2.22
     VT
    2.22
    Act Density 1.276%

    No Known Activations