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

    Neuronpedia

    INDEX
    Explanations

    living areas and their features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apprehended
    0.44
    bcrypt
    0.43
    rophiles
    0.43
    lahir
    0.42
    ulnerability
    0.42
     siglas
    0.41
     unethical
    0.40
    ویان
    0.40
     corruption
    0.39
     cryptography
    0.39
    POSITIVE LOGITS
     sofa
    0.88
     kitchenette
    0.88
     fireplace
    0.86
     bookcases
    0.84
     alc
    0.83
     sofas
    0.83
     wall
    0.80
     corner
    0.80
    客厅
    0.80
     dining
    0.79
    Act Density 0.027%

    No Known Activations