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

    Neuronpedia

    INDEX
    Explanations

    Beginning of text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    673
    -0.07
    Permissions
    -0.06
     Benedict
    -0.06
    faf
    -0.06
     Recorder
    -0.06
    	code
    -0.06
    endoza
    -0.06
     downward
    -0.06
    .ToLower
    -0.06
    _intent
    -0.06
    POSITIVE LOGITS
      ↵
    0.07
     못
    0.07
    구글상위
    0.06
     optarg
    0.06
    ,,,
    0.06
     піс
    0.06
    	memcpy
    0.06
    //}}
    0.06
     purpose
    0.06
    consin
    0.06
    Act Density 0.070%

    No Known Activations