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

    Neuronpedia

    INDEX
    Explanations

    increasingly difficult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hashMap
    0.48
     faiths
    0.47
    光
    0.47
    㙋
    0.46
     frauds
    0.46
    <unused294>
    0.45
    cidas
    0.45
    isierte
    0.44
    бята
    0.43
     விழுப்பு
    0.43
    POSITIVE LOGITS
     Microsoft
    0.52
     per
    0.46
     GmbH
    0.45
     Accommodation
    0.45
    ိုး
    0.44
     Factory
    0.44
     Rep
    0.43
     NS
    0.42
    目の
    0.42
     Concert
    0.42
    Act Density 0.001%

    No Known Activations