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

    Neuronpedia

    INDEX
    Explanations

    storage capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flask
    0.81
     AutoML
    0.80
     DataTable
    0.77
     dimethyl
    0.75
     mapper
    0.74
     Amplify
    0.74
     NAB
    0.74
     snack
    0.74
    枡
    0.74
     quarks
    0.74
    POSITIVE LOGITS
    打
    0.80
    which
    0.78
    United
    0.76
    canic
    0.75
     качестве
    0.74
    textit
    0.74
     打
    0.73
    Pear
    0.72
    Tower
    0.72
    espèce
    0.71
    Act Density 0.000%

    No Known Activations