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

    Neuronpedia

    INDEX
    Explanations

    Various text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ransomware
    -0.08
     inflamm
    -0.08
    adle
    -0.08
    eert
    -0.08
     porn
    -0.08
    不好
    -0.08
     Mohammed
    -0.08
    .infinity
    -0.08
     వచ్చ
    -0.08
     Angola
    -0.08
    POSITIVE LOGITS
    	parameters
    0.08
     اقتصادی
    0.07
     قاعدة
    0.07
     pit
    0.07
    ့
    0.07
     ಅ
    0.07
     ಗ್ರ
    0.07
     Quartz
    0.07
     அ
    0.07
     ocorrido
    0.06
    Act Density 0.000%

    No Known Activations