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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     активно
    -0.07
    �
    -0.07
    τέ
    -0.07
    (Parser
    -0.07
    ='<?
    -0.06
    -0.06
     وما
    -0.06
     dracon
    -0.06
    �
    -0.06
    縣
    -0.06
    POSITIVE LOGITS
     CREATE
    0.06
    ै?↵
    0.06
     --↵↵
    0.06
     plano
    0.06
     Survival
    0.06
     wanna
    0.06
    GR
    0.06
    _GRAPH
    0.06
     dominate
    0.06
     불
    0.06
    Act Density 0.001%

    No Known Activations