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

    Neuronpedia

    INDEX
    Explanations

    Disclaimer: I am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biodegradation
    0.50
     でしょう
    0.47
     decomposition
    0.46
     degradation
    0.45
     primordial
    0.45
     fragments
    0.45
     subsets
    0.45
     intelligible
    0.45
     Color
    0.44
     tumors
    0.43
    POSITIVE LOGITS
    pesar
    0.52
    Disclaimer
    0.50
    这款
    0.50
    Despite
    0.48
    私は
    0.46
    我是
    0.46
    从事
    0.45
    Celebrating
    0.44
    আমি
    0.44
    不喜欢
    0.43
    Act Density 0.026%

    No Known Activations