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

    Neuronpedia

    INDEX
    Explanations

    past time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     musí
    0.93
    current
    0.84
     നിങ്ങൾക്ക്
    0.82
     যতই
    0.81
    unless
    0.79
     পড়ছে
    0.78
    시면
    0.78
     পারছি
    0.77
     அல்லது
    0.77
     അല്ലെങ്കിൽ
    0.76
    POSITIVE LOGITS
     during
    3.01
     בשנת
    2.82
    during
    2.64
     During
    2.57
     durante
    2.50
    ในปี
    2.46
    During
    2.37
     vuonna
    2.34
     DURING
    2.32
     shortly
    2.32
    Act Density 0.582%

    No Known Activations