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

    Neuronpedia

    INDEX
    Explanations

    PV extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     барои
    0.48
    ámico
    0.46
     जेव्हा
    0.44
    าราง
    0.43
     nadie
    0.42
    ⺝
    0.42
     dargestellt
    0.41
    ছিল
    0.41
    वत्ता
    0.40
    Ked
    0.40
    POSITIVE LOGITS
    yl
    0.44
     forms
    0.44
     ovens
    0.43
     TPU
    0.43
     feature
    0.42
     loses
    0.42
     UK
    0.42
     vs
    0.42
     resident
    0.42
     gray
    0.42
    Act Density 0.002%

    No Known Activations