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

    Neuronpedia

    INDEX
    Explanations

    code formatting and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chaos
    0.86
     nervous
    0.71
     Byst
    0.70
     exos
    0.70
     મેળ
    0.70
     likeness
    0.69
     willing
    0.68
     Pyr
    0.68
     chaos
    0.67
     willingly
    0.67
    POSITIVE LOGITS
     ecma
    0.94
     ecmaVersion
    0.93
    eslint
    0.93
     jsx
    0.91
    typescript
    0.89
    prettier
    0.85
    禁止
    0.81
    jsx
    0.80
    TypeScript
    0.79
    camel
    0.78
    Act Density 0.059%

    No Known Activations