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

    Neuronpedia

    INDEX
    Explanations

    transitioning topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FhirExtension
    0.29
    ExtensionsPath
    0.28
     이는
    0.28
    Beverungen
    0.27
     נוס
    0.26
     texId
    0.25
     supplémentaires
    0.25
     unquestionably
    0.25
    ፥
    0.24
    ⓓ
    0.24
    POSITIVE LOGITS
     Anyway
    0.60
     Anyways
    0.60
    Anyway
    0.53
     anyways
    0.50
     anyway
    0.47
    Anyways
    0.46
     anyhow
    0.40
     Yeah
    0.38
    yeah
    0.37
     People
    0.36
    Act Density 0.021%

    No Known Activations