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

    Neuronpedia

    INDEX
    Explanations

    Full-Stack Developer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odia
    0.90
    ates
    0.79
    ches
    0.78
     অদৃশ্য
    0.78
    පා
    0.75
    geries
    0.74
    獪
    0.74
    abets
    0.73
     اہ
    0.73
     aDict
    0.71
    POSITIVE LOGITS
     deeper
    0.73
     always
    0.71
    stack
    0.68
    service
    0.67
     hexa
    0.66
     somehow
    0.64
    িত্ত
    0.64
    深入
    0.63
     dress
    0.62
    always
    0.62
    Act Density 0.007%

    No Known Activations