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

    Neuronpedia

    INDEX
    Explanations

    code snippets and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensity
    0.46
    ექტ
    0.43
     Amherst
    0.43
    넬
    0.42
    Kelly
    0.41
    έρα
    0.40
     Newell
    0.40
    AWSJavaScriptSDK
    0.40
    蓖
    0.40
     하기
    0.39
    POSITIVE LOGITS
     incipient
    0.41
     viu
    0.40
     sprays
    0.40
     aggressive
    0.39
    pairs
    0.38
     meds
    0.38
     फायदे
    0.38
     flares
    0.38
     குர
    0.38
     sino
    0.38
    Act Density 0.088%

    No Known Activations