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

    Neuronpedia

    INDEX
    Explanations

    words starting with sub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Resol
    0.66
     Shed
    0.62
    та
    0.61
    о
    0.61
    на
    0.57
     Schr
    0.56
    的时
    0.55
    μο
    0.54
    ص
    0.54
     Spa
    0.54
    POSITIVE LOGITS
     sub
    0.94
     subgoal
    0.93
     subnet
    0.91
     subwoofer
    0.84
     суб
    0.80
     subd
    0.80
    サブ
    0.71
     subgroups
    0.69
     subgroup
    0.69
    getSub
    0.69
    Act Density 0.047%

    No Known Activations