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

    Neuronpedia

    INDEX
    Explanations

    regenerated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engagements
    -0.06
    ۱
    -0.06
     undone
    -0.06
    tri
    -0.06
     Tên
    -0.06
    PIC
    -0.06
    tec
    -0.06
    igos
    -0.06
    áhl
    -0.06
     빌
    -0.06
    POSITIVE LOGITS
    xE
    0.07
     Calculates
    0.07
    	↵↵↵
    0.07
     �
    0.07
    -Cola
    0.07
    firstName
    0.07
    094
    0.07
     coordinating
    0.07
        ↵↵↵
    0.06
    Doctrine
    0.06
    Act Density 0.001%

    No Known Activations