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

    Neuronpedia

    INDEX
    Explanations

    stdlib.h inclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allocate
    0.46
     Subdistrict
    0.42
    ंसारी
    0.41
    ဵ
    0.40
    allocated
    0.39
    لينكات
    0.38
     ResourceManager
    0.38
    ミルク
    0.38
     Allocated
    0.38
    0.38
    POSITIVE LOGITS
     h
    0.67
     hmm
    0.53
    h
    0.52
     H
    0.50
    stdio
    0.49
     hm
    0.47
    Hmm
    0.46
     Hmm
    0.44
     huh
    0.44
    hmm
    0.42
    Act Density 0.002%

    No Known Activations