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

    Neuronpedia

    INDEX
    Explanations

    time differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vegan
    -0.06
     /****************************************************************
    -0.06
     Savior
    -0.06
     písem
    -0.06
    	JSONObject
    -0.06
     biography
    -0.06
    参加
    -0.06
     �
    -0.06
    -summary
    -0.06
     upstairs
    -0.06
    POSITIVE LOGITS
    ÜM
    0.07
     acquisitions
    0.07
    مز
    0.06
    كر
    0.06
    ुप
    0.06
    assume
    0.06
    öm
    0.06
    histoire
    0.06
    ख
    0.06
    ôte
    0.06
    Act Density 0.001%

    No Known Activations