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

    Neuronpedia

    INDEX
    Explanations

    categorizing information or learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mem
    0.44
    מ
    0.42
    Blooming
    0.42
    Ciudad
    0.41
     mismo
    0.41
    Dest
    0.41
    Neighborhood
    0.40
     Bloomington
    0.40
     समुदाय
    0.39
    Aurora
    0.39
    POSITIVE LOGITS
     actuar
    0.49
     learnt
    0.45
     Wales
    0.45
     insurance
    0.43
     arrears
    0.43
    insurance
    0.43
     BSc
    0.42
     medico
    0.41
     somebody
    0.41
     букмекердик
    0.41
    Act Density 0.009%

    No Known Activations