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

    Neuronpedia

    INDEX
    Explanations

    English proficiency breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discussing
    0.43
    measurement
    0.40
     weren
    0.39
     yourselves
    0.39
     mouths
    0.38
     zmian
    0.38
     discussion
    0.38
     mudanças
    0.38
     getInput
    0.37
     meantime
    0.37
    POSITIVE LOGITS
    <unused2164>
    0.50
    Corollary
    0.49
    ніципа
    0.48
    来自于
    0.47
    cích
    0.46
    jährige
    0.42
    nę
    0.42
    Streaming
    0.42
     بہت
    0.42
    FBSDKLogin
    0.42
    Act Density 0.002%

    No Known Activations