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

    Neuronpedia

    INDEX
    Explanations

    actions or processes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लेखन
    0.39
     Pestic
    0.38
     Được
    0.38
    Filling
    0.37
     Evaluación
    0.36
    Ꮿ
    0.35
     explicando
    0.35
     Filling
    0.35
     Thành
    0.35
    Navigation
    0.34
    POSITIVE LOGITS
     include
    0.80
     introduce
    0.71
     use
    0.70
     create
    0.67
     put
    0.64
     employ
    0.63
     treat
    0.63
     randomize
    0.63
     implement
    0.62
     inject
    0.62
    Act Density 1.992%

    No Known Activations