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

    Neuronpedia

    INDEX
    Explanations

    create customized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compétence
    0.51
     pienso
    0.49
     estou
    0.48
     computadora
    0.47
     estudiantes
    0.46
    હિ
    0.46
     estoque
    0.45
    なども
    0.45
    ўцаў
    0.44
     düşünüyorum
    0.43
    POSITIVE LOGITS
     derailed
    0.51
     Indicates
    0.46
     Basic
    0.46
     External
    0.45
    at
    0.44
     Nimbus
    0.44
     lacked
    0.43
     pulls
    0.42
     அடிப்படை
    0.42
     indicated
    0.42
    Act Density 0.002%

    No Known Activations