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

    Neuronpedia

    INDEX
    Explanations

    Industries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geile
    -0.08
     oči
    -0.07
    Dirty
    -0.07
    ículos
    -0.07
    Speak
    -0.07
    Robin
    -0.06
     �
    -0.06
     Beste
    -0.06
    िकल
    -0.06
     prům
    -0.06
    POSITIVE LOGITS
    Retention
    0.07
     Mathematical
    0.07
     Ada
    0.07
     Identifier
    0.06
    ="")↵
    0.06
     "__
    0.06
     inadvert
    0.06
    ="<?
    0.06
    .Ma
    0.06
     audible
    0.06
    Act Density 0.078%

    No Known Activations