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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    พระ
    0.55
    ستم
    0.54
    akir
    0.53
    BES
    0.52
     mengalami
    0.52
    潴
    0.52
     ड्राइव
    0.51
    SampleSize
    0.51
     GetComponent
    0.51
    MUL
    0.50
    POSITIVE LOGITS
     vassals
    0.63
     virtuous
    0.60
     shader
    0.59
     putt
    0.59
     lured
    0.57
     assets
    0.57
     gai
    0.57
     transitioned
    0.56
     വിജ
    0.56
     miembros
    0.55
    Act Density 0.001%

    No Known Activations