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

    Neuronpedia

    INDEX
    Explanations

    Java/Kotlin annotations and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brothers
    0.43
     yaml
    0.43
     jana
    0.41
     jaaye
    0.41
     JavaBean
    0.41
    FBSDKError
    0.41
     tensorflow
    0.40
     milliseconds
    0.40
     thửa
    0.40
    ினா
    0.40
    POSITIVE LOGITS
    Universität
    0.37
    㳑
    0.35
    整理
    0.34
    acency
    0.34
     таке
    0.34
    maturity
    0.34
    bona
    0.33
    صف
    0.33
    valent
    0.33
    éral
    0.33
    Act Density 0.001%

    No Known Activations