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

    Neuronpedia

    INDEX
    Explanations

    tables and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ---------------
    0.53
     --------------
    0.44
     ---------
    0.44
     -------------
    0.40
     ---
    0.39
     -------
    0.39
     borderColor
    0.39
     --------");
    0.38
     रक्त
    0.38
     ------------
    0.38
    POSITIVE LOGITS
     enterprise
    0.40
     amplify
    0.38
     benefit
    0.38
    enterprise
    0.37
     کمپنیوں
    0.36
    mills
    0.35
    Enterprise
    0.35
     ami
    0.33
     شام
    0.32
     microphones
    0.32
    Act Density 0.016%

    No Known Activations