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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Operation
    -0.07
                            
↵
    -0.07
     manufact
    -0.07
    )}↵↵
    -0.07
     
↵
    -0.06
     Languages
    -0.06
     BorderSide
    -0.06
    ('^
    -0.06
    _AGENT
    -0.06
     EventType
    -0.06
    POSITIVE LOGITS
     kk
    0.06
    iators
    0.06
    rive
    0.06
    ัคร
    0.06
     зуп
    0.06
     Wendy
    0.06
    ervo
    0.06
     zim
    0.06
    Theta
    0.06
     паль
    0.06
    Act Density 0.007%

    No Known Activations