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

    Neuronpedia

    INDEX
    Explanations

    continue to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Continuous
    0.63
     Contin
    0.62
     Continuing
    0.61
    Continuous
    0.53
    Contin
    0.53
     continu
    0.52
     Continu
    0.52
     continuing
    0.51
     continuare
    0.51
    Continuing
    0.51
    POSITIVE LOGITS
     unab
    0.74
     indefinitely
    0.74
     onward
    0.68
    下去
    0.62
     onwards
    0.60
     refining
    0.57
     uninterrupted
    0.57
     unchanged
    0.56
     saga
    0.55
     unbroken
    0.52
    Act Density 0.030%

    No Known Activations