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

    Neuronpedia

    INDEX
    Explanations

    access to compensation, terminology, complex systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘩
    0.59
    𝘦
    0.48
    𝘫
    0.47
     advancing
    0.47
    ریق
    0.47
    われた
    0.46
    icznej
    0.46
    ুবাদ
    0.45
     আকারে
    0.45
    𝘤
    0.45
    POSITIVE LOGITS
    ).
    0.44
    圈
    0.43
     bạn
    0.43
     xung
    0.40
     sens
    0.38
     wom
    0.37
    ť
    0.37
    /
    0.37
     rectal
    0.37
     tentativa
    0.37
    Act Density 0.000%

    No Known Activations