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

    Neuronpedia

    INDEX
    Explanations

    forming a conical shape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Top
    0.49
    1
    0.49
    2
    0.47
     and
    0.46
    initi
    0.45
     Top
    0.45
    Ant
    0.43
    a
    0.43
     legitim
    0.42
     reorgan
    0.41
    POSITIVE LOGITS
     ජී
    0.51
     maraming
    0.50
     ப்ளாக்
    0.50
     учетом
    0.50
    槳
    0.48
     muchas
    0.47
     Pharisees
    0.46
    kang
    0.46
    arey
    0.46
     ماشینونو
    0.46
    Act Density 0.001%

    No Known Activations