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

    Neuronpedia

    INDEX
    Explanations

    say "{"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cigarettes
    -0.07
    WebView
    -0.07
    โค
    -0.06
    obody
    -0.06
     února
    -0.06
     equivalence
    -0.06
     masses
    -0.06
    只能
    -0.06
    Ст
    -0.06
     ILogger
    -0.06
    POSITIVE LOGITS
    wrong
    0.07
     yeme
    0.07
     जह
    0.06
    �
    0.06
    Nd
    0.06
     �
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
     otom
    0.06
    	break
    0.06
     กล
    0.06
    Act Density 0.017%

    No Known Activations