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

    Neuronpedia

    INDEX
    Explanations

    operation inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dikutip
    0.52
     remarked
    0.51
    noticed
    0.40
    quoted
    0.40
     remarqué
    0.39
     noticed
    0.37
    时
    0.37
    鿓
    0.37
     queried
    0.36
     comentó
    0.36
    POSITIVE LOGITS
    imba
    0.46
     molecule
    0.44
     Tand
    0.43
     glass
    0.42
     tamb
    0.41
     tandem
    0.40
     tek
    0.40
     Tamb
    0.39
     состав
    0.39
     jab
    0.38
    Act Density 0.000%

    No Known Activations