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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thought
    -0.07
     grop
    -0.07
     our
    -0.07
    'I
    -0.06
    Blueprint
    -0.06
     {
↵
↵
↵
    -0.06
     muc
    -0.06
    >'.↵
    -0.06
     videos
    -0.06
     피
    -0.06
    POSITIVE LOGITS
    湍
    0.08
     Conditional
    0.07
     unify
    0.07
     arasında
    0.07
     loadChildren
    0.06
    宽
    0.06
    雍
    0.06
    เขต
    0.06
    蛄
    0.06
    丧失
    0.06
    Act Density 0.069%

    No Known Activations