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

    Neuronpedia

    INDEX
    Explanations

    javascript code and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ふわ
    0.38
    льными
    0.36
    Induced
    0.36
    驱
    0.35
    瘟
    0.35
    Kunst
    0.35
    的两
    0.35
     périph
    0.34
    FBSDKError
    0.34
    льным
    0.34
    POSITIVE LOGITS
     मिनि
    0.45
     talked
    0.45
     подозре
    0.43
     Lucille
    0.40
     Singapura
    0.39
     Например
    0.39
     Futuristic
    0.39
     stockpile
    0.38
     सर्विसेज
    0.38
    emplates
    0.38
    Act Density 0.000%

    No Known Activations