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

    Neuronpedia

    INDEX
    Explanations

    data keys and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispatch
    -0.07
     Pointer
    -0.06
    IDX
    -0.06
     '{"
    -0.06
    계
    -0.06
     Stuff
    -0.06
    (*)(
    -0.06
    GOOD
    -0.06
     WF
    -0.06
     geben
    -0.06
    POSITIVE LOGITS
     aktuální
    0.07
    ницип
    0.07
     drž
    0.07
     Represent
    0.06
            
↵
↵
    0.06
     �
    0.06
     ‎
    0.06
        
↵
↵
    0.06
     adventure
    0.06
    Yellow
    0.06
    Act Density 0.021%

    No Known Activations