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

    Neuronpedia

    INDEX
    Explanations

    capital city of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fungicide
    0.60
     troubleshoot
    0.57
     troubleshooting
    0.56
     TPM
    0.55
     PDA
    0.54
     dyslex
    0.54
     psyched
    0.54
     usability
    0.54
     debugging
    0.52
     Hepatitis
    0.52
    POSITIVE LOGITS
    ío
    0.61
    emn
    0.60
     majest
    0.59
    anaa
    0.59
    ().
    0.58
    president
    0.57
    🇫
    0.57
    countable
    0.56
    。
    0.56
    esho
    0.55
    Act Density 0.017%

    No Known Activations